CN112115644A - Neural network-based method for predicting intermediate-frequency sound absorption coefficient of open-cell foamed aluminum with composite structure - Google Patents
Neural network-based method for predicting intermediate-frequency sound absorption coefficient of open-cell foamed aluminum with composite structure Download PDFInfo
- Publication number
- CN112115644A CN112115644A CN202010976228.XA CN202010976228A CN112115644A CN 112115644 A CN112115644 A CN 112115644A CN 202010976228 A CN202010976228 A CN 202010976228A CN 112115644 A CN112115644 A CN 112115644A
- Authority
- CN
- China
- Prior art keywords
- open
- sound absorption
- neural network
- composite structure
- cell
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 title claims abstract description 76
- 238000010521 absorption reaction Methods 0.000 title claims abstract description 70
- 229910052782 aluminium Inorganic materials 0.000 title claims abstract description 70
- 239000002131 composite material Substances 0.000 title claims abstract description 66
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000000306 recurrent effect Effects 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 239000006260 foam Substances 0.000 claims description 28
- 239000011148 porous material Substances 0.000 claims description 8
- 238000002790 cross-validation Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 abstract description 6
- 238000002474 experimental method Methods 0.000 abstract description 4
- 238000009499 grossing Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000001419 dependent effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- -1 porosity Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/10—Noise analysis or noise optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses a neural network-based method for predicting the medium-frequency sound absorption coefficient of open-cell foamed aluminum with a composite structure, which designs a double-layer composite structure; determining influence factors influencing the sound absorption capacity of the open-cell foamed aluminum, determining sound absorption coefficients of various different composite structures under the influence factors and sound sources with different frequencies, and obtaining data sets corresponding to the influence factors and the sound absorption coefficients of the various different composite structures; dividing the data set into a training sample and a testing sample; establishing a generalized recurrent neural network by using a newgrnn function of MATLAB, and training and testing the generalized recurrent neural network through the training sample and the test sample to obtain a final generalized recurrent neural network; and during prediction, inputting the influence factors of the composite structure to be predicted into the final generalized regression neural network, and predicting the sound absorption coefficient of the composite structure. The method can quickly predict the sound absorption coefficient of the double-layer composite structure with the cavity without heavy experiments.
Description
Technical Field
The method relates to the field of sound absorption and noise reduction, in particular to a method for predicting the medium-frequency sound absorption coefficient of open-cell foamed aluminum with a composite structure based on a neural network.
Background
At present, solving the problem of noise pollution is an urgent matter. The sound absorption principle of the sound absorption material or structure mainly comprises a resonance sound absorption principle and a porous sound absorption principle. The single sound absorption material is difficult to meet the requirements of people on sound absorption and noise reduction, so that the development and application of a composite structure are more and more emphasized by people, but for the design of the composite structure, the sound absorption coefficient is mostly measured to obtain the parameter range of the composite structure with relatively excellent performance, but the method is heavy in workload and large in error of a test result, and therefore a frequency sound absorption coefficient prediction method which is simple and convenient in process, rapid and accurate in prediction result is urgently needed.
Disclosure of Invention
The invention aims to overcome the defects, and provides a method for predicting the medium-frequency sound absorption coefficient of the open-cell foamed aluminum with the composite structure based on the neural network.
In order to realize the purpose of the invention, the concrete steps are as follows:
a neural network-based method for predicting the medium-frequency sound absorption coefficient of open-cell foamed aluminum with a composite structure comprises the following steps:
s1, designing a composite structure, wherein the composite structure comprises a first layer of open-cell foamed aluminum, a second layer of open-cell foamed aluminum and a rigid wall which are sequentially arranged in parallel, and back cavities are respectively arranged between the first layer of open-cell foamed aluminum and the second layer of open-cell foamed aluminum and between the second layer of open-cell foamed aluminum and the rigid wall;
s2, combining a plurality of different composite structures by adopting a first layer of open-cell foamed aluminum with different thicknesses, a second layer of open-cell foamed aluminum with different thicknesses and back cavities with different depths;
s3, determining influence factors influencing the sound absorption capacity of the open-cell foamed aluminum, determining sound absorption coefficients of the various composite structures obtained in the S2 under the influence factors and sound sources with different frequencies, and obtaining data sets corresponding to the influence factors and the sound absorption coefficients of the various composite structures;
s4, dividing the data set obtained in the S3 into a training sample and a testing sample;
s5, creating a generalized recurrent neural network by using a newgrnn function of MATLAB, and training and testing the generalized recurrent neural network through the training sample and the test sample to obtain a final generalized recurrent neural network;
and S6, inputting the influence factors of the composite structure to be predicted into the final generalized regression neural network obtained in the step S5 during prediction, and predicting the sound absorption coefficient of the composite structure.
Preferably, the density of the first layer of open-cell aluminum foam is 0.856g/cm3Porosity of 68.296%, pore diameter of 90X 10-6m, the thickness is 4-12 mm.
Preferably, the second layer of open-cell aluminum foam has a density of 0.898g/cm3Porosity of 66.741%, pore diameter of 78X 10-6m, the thickness is 4-12 mm.
Preferably, the depth of the back cavity between the first layer of open-cell aluminum foam and the second layer of open-cell aluminum foam is 0-50mm, and the depth of the back cavity between the second layer of open-cell aluminum foam and the rigid wall is 0-50 mm.
Preferably, in S3, the standing wave tube method is used to measure the influencing factors affecting the sound absorption capacity of the open-cell aluminum foam, including porosity, pore size, density, thickness and cavity depth behind.
Preferably, in S3, the frequencies of the sound source include 500Hz, 800Hz, 1000Hz, 1250Hz, and 1600 Hz.
Preferably, in S5, the generalized recurrent neural network determines the optimal width coefficient of the gaussian function by using the gaussian function as the basis function, and after establishing the generalized neural network and selecting the optimal width coefficient, the generalized recurrent neural network is created by using the newgrnn function of the MATLAB itself.
Preferably, the optimal width coefficient is determined by using a K-fold cross validation method, and the determined optimal width coefficient is 0.1.
The invention has the following beneficial effects:
the method for predicting the intermediate-frequency sound absorption coefficient of the open-cell foamed aluminum with the composite structure based on the neural network can predict the sound absorption coefficient by determining the generalized regression neural network and adopting the generalized regression neural network, when predicting, the influence factors of the composite structure to be predicted are input into the generalized regression neural network, the specific values of the influence factors in the composite structure combination with the optimal sound absorption effect under a certain frequency can be obtained by observing the prediction result of the sound absorption coefficient by adjusting the influence factors influencing the sound absorption capacity of the open-cell foamed aluminum, wherein for a certain composite structure, the parameters of the first layer of open-cell foamed aluminum and the second layer of open-cell foamed aluminum are determined, so that only the depth of a cavity between the first layer of open-cell foamed aluminum and the second layer of open-cell foamed aluminum and the depth of a cavity between the second layer of open-cell foamed aluminum and a rigid wall are required to be adjusted, when the method is adopted to predict the medium-frequency sound absorption coefficient of the open-cell foamed aluminum with the composite structure, the medium-frequency sound absorption coefficient is determined without carrying out heavy experiments, so that the design efficiency of the composite structure with excellent performance can be improved; by using the method, the relative error of the prediction result is 6.9 percent at most and 2.1 percent at least, and the error of the prediction result is small.
Drawings
FIG. 1 is a construction diagram of a composite structure designed in the present invention;
FIG. 2 is a schematic diagram showing a comparison of a predicted value and a true value of a sound absorption coefficient of a composite structure at 500Hz according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of relative errors between predicted values and actual values of sound absorption coefficients of five test samples at 500Hz in the embodiment of the present invention;
FIG. 4 is a flowchart of a generalized recurrent neural network algorithm in an embodiment of the present invention.
In the figure, 1-the first layer of open-cell aluminum foam, 2-the second layer of open-cell aluminum foam, 3-the rigid wall, 4-the back cavity.
Detailed Description
The invention is further illustrated with reference to the figures and examples.
The invention relates to a method for predicting the medium-frequency sound absorption coefficient of open-cell foamed aluminum with a composite structure based on a neural network, which comprises the following steps of:
step 1: the composite structure is designed, the composite structure adopts three first layers of open-cell foamed aluminum 1 with different thicknesses and 3 second layers of open-cell foamed aluminum 2 with different thicknesses to form 20 composite structures, the structural diagram of the composite structure is shown in figure 1, a cavity (namely a back cavity 4) exists between the first layer of open-cell foamed aluminum 1 and the second layer of open-cell foamed aluminum 2, and a cavity (namely the back cavity 4) also exists between the second layer of open-cell foamed aluminum 2 and the rigid wall 3. The basic parameters of the first layer of open-cell aluminum foam 1 and the second layer of open-cell aluminum foam 2 are shown in Table 1, and the density of the first layer of open-cell aluminum foam 1 (indicated as A in Table 1) is 0.856g/cm3Porosity of 68.296%, pore diameter of 90X 10-6m, the thickness is respectively 4mm, 8mm and 12mm, and the depth of the back cavity is selected from 0mm, 10mm, 20mm, 30mm, 40mm and 50 mm; the second layer of open-cell aluminum foam 2 (indicated as B in Table 1) had a density of 0.898g/cm3Porosity of 66.741%, pore diameter of 78X 10-6m, the thickness is 4mm, 8mm and 12mm respectively, and the back cavity depth is selected from 0mm, 10mm, 20mm, 30mm, 40mm and 50 mm. Specific combinations of the 20 composite structures are shown in table 2, wherein a represents a first layer of open cell aluminum foam 1, B represents a second layer of open cell aluminum foam 2, L represents the back cavity, the A, B subscripts indicate the thickness of the first and second layers of open cell aluminum foam 1 and 2, respectively, and are reported in table 1, and the L subscript indicates the back cavity depth.
Step 2: determining influence factors and acquiring target data, wherein the target data adopts a standing wave tube method to measure sound absorption coefficients of 20 combinations designed according to 5 influence factors (porosity, aperture, density, thickness and back cavity depth) influencing sound absorption capacity of the foamed aluminum under sound source frequencies of 500Hz, 800Hz, 1000Hz, 1250Hz and 1600 Hz;
and step 3: dividing a training sample and a test sample, performing sample definition (20 groups of samples) and sample division on 20 measured groups of data by using MATLAB, selecting samples from No. 1 to No. 15 (referring to a table 2) as the training sample, and selecting samples from No. 16 to No. 20 as the test sample;
and 4, step 4: and (3) determining a smooth factor, wherein the generalized regression neural network adopts a Gaussian function as a basis function. The width coefficient of the gaussian function, also called the smoothing factor alpha, is poor in prediction effect when the value of the smoothing factor alpha tends to zero, and is approximate to the average value of all sample dependent variables when the value is too large. Therefore, the optimal smoothing factor α is first determined by K-fold cross-validation. The method comprises the following specific steps:
the first step is as follows: the initial sample is divided into 4 subsamples, one single subsample is kept as data for the verification model, and the other 3 samples are used for training.
The second step is that: cross-validation was 4 times, once for each subsample.
The third step: the four results were averaged to finally obtain a single estimate.
The final optimal smoothing factor α was 0.1.
And 5: the algorithm flow chart of the generalized neural network is shown in fig. 4. After the optimal smoothing factor is selected, a generalized recurrent neural network is created by using a newgrnn function of the MATLAB self-band and is trained. The prediction is carried out by using a trained generalized recurrent neural network, and the flow chart of the algorithm is shown in FIG. 4.
Step 6: and (3) forecasting evaluation, namely, a graph of a predicted value and a real value and analysis of relative errors of the predicted value and the real value are carried out through the graphs in the figures 2 and 3, and the forecasting capability of the model is found to be ideal.
TABLE 1
TABLE 2
Therefore, the method for predicting the medium-frequency sound absorption coefficient of the open-cell foamed aluminum with the composite structure based on the neural network designs the double-layer composite structure with the cavity, and the sound absorption coefficient of the composite structure is predicted by adopting the generalized regression neural network. The subsidiary cavity structure solves the problem of low sound absorption coefficient of the composite structure, the specific value of the depth of the back cavity in the composite structure combination with the optimal sound absorption effect under a certain frequency can be obtained by adjusting the numerical value input of the depth of the back cavity to observe the prediction result of the sound absorption coefficient, and the determination is not required to be carried out through heavy experiments.
Examples
The following description is made by taking the sound absorption coefficient prediction case at 500Hz according to the designed composite structure:
step 1: the sound absorption coefficients of the 20 composite structures under 500Hz are measured by using a standing wave tube, and the specific numerical values are shown in Table 2;
step 2: using MATLAB to carry out sample definition (20 groups of samples) and sample division on the measured 20 groups of data, and selecting samples from No. 1 to No. 15 as training samples and samples from No. 16 to No. 20 as test samples;
and step 3: and (3) determining a smooth factor, wherein the generalized regression neural network adopts a Gaussian function as a basis function. The width coefficient of the gaussian function, also called the smoothing factor alpha, is poor in prediction effect when the value of the smoothing factor alpha tends to zero, and is approximate to the average value of all sample dependent variables when the value is too large. Therefore, the optimal smoothing factor α is first determined by K-fold cross-validation.
The final optimal smoothing factor α was 0.1.
And 4, step 4: after the optimal smooth factor is selected for establishing the generalized neural network, the generalized recurrent neural network is created by using a newgrnn function carried by MATLAB, and is trained. And (4) predicting by using the trained generalized recurrent neural network.
And 5: a fit of predicted and true values was obtained in a MATLAB plot, as shown in fig. 4. The relative error between the predicted value and the true value was calculated by a program, and as shown in FIG. 3, the average relative error at 500Hz was only 6.94%.
Through the radial basis function network, only a few basic structure parameters which are easy to measure are needed to design the composite structure.
In conclusion, the invention has the following advantages:
firstly, the invention designs a composite structure with a cavity as shown in fig. 1, so that the open-cell foamed aluminum and the back cavity form a helmholtz resonance structure, the composite structure has porous sound absorption and resonance sound absorption at the same time, the sound absorption performance of the composite structure is improved, the average sound absorption coefficient of the composite structure under different frequencies can reach 0.82 at the lowest, and can reach 0.90 at the highest, and the peak value of the sound absorption coefficient can reach 0.991 at 1000 Hz.
Secondly, the selection of the depth of the cavity behind directly affects the sound absorption performance of the composite structure, and the sound absorption coefficient is reduced if the selection is too large or too small. The sound absorption coefficient prediction method adopts the generalized regression neural network to predict the sound absorption coefficient, and the specific value of the depth of the back cavity in the composite structure combination with the optimal sound absorption effect under a certain frequency can be obtained by adjusting the numerical value input of the depth of the back cavity to observe the prediction result of the sound absorption coefficient, and the sound absorption coefficient prediction method does not need to carry out heavy experiments to determine.
Thirdly, the generalized regression neural network is adopted for prediction, a training model can be obtained by using less required data, and only 15 groups of data are required for training.
Fourthly, the relative error of the prediction result is 6.9 percent at most and 2.1 percent at least, the prediction capability of the designed prediction model in the intermediate frequency range is very ideal, and the sound absorption frequency range of the model prediction composite structure open-cell foamed aluminum is in the intermediate frequency range of 800Hz-1600 Hz.
Claims (8)
1. A method for predicting the medium-frequency sound absorption coefficient of open-cell foamed aluminum with a composite structure based on a neural network is characterized by comprising the following steps of:
s1, designing a composite structure, wherein the composite structure comprises a first layer of open-cell foamed aluminum (1), a second layer of open-cell foamed aluminum (2) and a rigid wall (3), which are sequentially arranged in parallel, and back cavities (4) are respectively arranged between the first layer of open-cell foamed aluminum (1) and the second layer of open-cell foamed aluminum (2) and between the second layer of open-cell foamed aluminum (2) and the rigid wall (3);
s2, combining a plurality of different composite structures by adopting a first layer of open-cell foamed aluminum (1) with different thicknesses, a second layer of open-cell foamed aluminum (2) with different thicknesses and back cavities (4) with different depths;
s3, determining influence factors influencing the sound absorption capacity of the open-cell foamed aluminum, determining sound absorption coefficients of the various composite structures obtained in the S2 under the influence factors and sound sources with different frequencies, and obtaining data sets corresponding to the influence factors and the sound absorption coefficients of the various composite structures;
s4, dividing the data set obtained in the S3 into a training sample and a testing sample;
s5, creating a generalized recurrent neural network by using a newgrnn function of MATLAB, and training and testing the generalized recurrent neural network through the training sample and the test sample to obtain a final generalized recurrent neural network;
and S6, inputting the influence factors of the composite structure to be predicted into the final generalized regression neural network obtained in the step S5 during prediction, and predicting the sound absorption coefficient of the composite structure.
2. The neural network-based method for predicting the mid-frequency sound absorption coefficient of open-cell aluminum foam with composite structure according to claim 1, wherein the density of the first layer of open-cell aluminum foam (1) is 0.856g/cm3Porosity of 68.296%, pore diameter of 90X 10-6m, the thickness is 4-12 mm.
3. The neural network-based method for predicting the mid-frequency sound absorption coefficient of open-cell aluminum foam with composite structure according to claim 1, wherein the density of the second layer of open-cell aluminum foam (2) is 0.898g/cm3Porosity of 66.741%, pore diameter of 78X 10-6m, the thickness is 4-12 mm.
4. The neural network-based method for predicting the middle-frequency sound absorption coefficient of the open-cell aluminum foam with the composite structure according to claim 1, wherein the depth of the back cavity (4) between the first layer of the open-cell aluminum foam (1) and the second layer of the open-cell aluminum foam (2) is 0-50mm, and the depth of the back cavity (4) between the second layer of the open-cell aluminum foam (2) and the rigid wall (3) is 0-50 mm.
5. The neural network-based method for predicting the middle-frequency sound absorption coefficient of the open-cell aluminum foam with the composite structure according to claim 1, wherein in S3, the influence factors influencing the sound absorption capacity of the open-cell aluminum foam are measured by a standing wave tube method, and the influence factors comprise porosity, pore diameter, density, thickness and back cavity depth.
6. The neural network-based method for predicting the mid-frequency sound absorption coefficient of open-cell aluminum foam of composite structure according to claim 1, wherein the frequencies of the sound source in S3 include 500Hz, 800Hz, 1000Hz, 1250Hz and 1600 Hz.
7. The method for predicting the mid-frequency sound absorption coefficient of open-cell aluminum foam with composite structure based on neural network as claimed in claim 1, wherein in S5, the generalized recurrent neural network uses gaussian function as the basis function to determine the optimal width coefficient of gaussian function, and after establishing the selected optimal width coefficient, the generalized recurrent neural network is created by using the newgrnn function of MATLAB self.
8. The neural network-based method for predicting the medium-frequency sound absorption coefficient of the open-cell aluminum foam with the composite structure according to claim 7, wherein an optimal width coefficient is determined by a K-fold cross validation method, and the determined optimal width coefficient is 0.1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010976228.XA CN112115644A (en) | 2020-09-16 | 2020-09-16 | Neural network-based method for predicting intermediate-frequency sound absorption coefficient of open-cell foamed aluminum with composite structure |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010976228.XA CN112115644A (en) | 2020-09-16 | 2020-09-16 | Neural network-based method for predicting intermediate-frequency sound absorption coefficient of open-cell foamed aluminum with composite structure |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112115644A true CN112115644A (en) | 2020-12-22 |
Family
ID=73803197
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010976228.XA Withdrawn CN112115644A (en) | 2020-09-16 | 2020-09-16 | Neural network-based method for predicting intermediate-frequency sound absorption coefficient of open-cell foamed aluminum with composite structure |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112115644A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112908433A (en) * | 2021-01-15 | 2021-06-04 | 西安建筑科技大学 | Method for calculating sound absorption coefficient of double-layer composite structure open-cell foamed aluminum based on dimensional analysis |
CN112966804A (en) * | 2021-02-03 | 2021-06-15 | 西安建筑科技大学 | Method and system for predicting foam copper sound absorption coefficient based on GRNN neural network optimization balance algorithm |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104654024A (en) * | 2015-02-12 | 2015-05-27 | 常州大学 | Method for locating and analyzing leakage of city gas pipeline based on GRNN (Generalized Regression Neural Network) |
CN106779151A (en) * | 2016-11-14 | 2017-05-31 | 中南大学 | A kind of line of high-speed railway wind speed multi-point multi-layer coupling prediction method |
CN206460780U (en) * | 2016-11-30 | 2017-09-01 | 西安建筑科技大学 | Plus the multilayer open celled foam aluminium sheet sound absorption structure of cavity |
WO2018090657A1 (en) * | 2016-11-18 | 2018-05-24 | 同济大学 | Bp_adaboost model-based method and system for predicting credit card user default |
-
2020
- 2020-09-16 CN CN202010976228.XA patent/CN112115644A/en not_active Withdrawn
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104654024A (en) * | 2015-02-12 | 2015-05-27 | 常州大学 | Method for locating and analyzing leakage of city gas pipeline based on GRNN (Generalized Regression Neural Network) |
CN106779151A (en) * | 2016-11-14 | 2017-05-31 | 中南大学 | A kind of line of high-speed railway wind speed multi-point multi-layer coupling prediction method |
WO2018090657A1 (en) * | 2016-11-18 | 2018-05-24 | 同济大学 | Bp_adaboost model-based method and system for predicting credit card user default |
CN206460780U (en) * | 2016-11-30 | 2017-09-01 | 西安建筑科技大学 | Plus the multilayer open celled foam aluminium sheet sound absorption structure of cavity |
Non-Patent Citations (2)
Title |
---|
DONG GUAN等: "Acoustic performance of aluminum foams with semiopen cells", APPLIED ACOUSTICS, vol. 2015, no. 87, 18 July 2014 (2014-07-18), pages 103 - 108 * |
梁李斯等: "Radial Basis Function Neural Network for prediction of mediumfrequency sound absorption coefficient of composite structure open-cell aluminum foam", APPLIED ACOUSTICS, vol. 2020, no. 170, 11 July 2020 (2020-07-11), pages 107505 - 107511 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112908433A (en) * | 2021-01-15 | 2021-06-04 | 西安建筑科技大学 | Method for calculating sound absorption coefficient of double-layer composite structure open-cell foamed aluminum based on dimensional analysis |
CN112966804A (en) * | 2021-02-03 | 2021-06-15 | 西安建筑科技大学 | Method and system for predicting foam copper sound absorption coefficient based on GRNN neural network optimization balance algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112115644A (en) | Neural network-based method for predicting intermediate-frequency sound absorption coefficient of open-cell foamed aluminum with composite structure | |
McGrory et al. | Sound absorption coefficient measurement: Re-examining the relationship between impedance tube and reverberant room methods | |
CN109625156B (en) | Ship full-band cabin noise forecasting and acoustic optimization design method | |
Cobo et al. | A wideband triple-layer microperforated panel sound absorber | |
Pieren et al. | Predicting sound absorption coefficients of lightweight multilayer curtains using the equivalent circuit method | |
Dias et al. | Sound absorbtion in knitted structures for interior noise reduction in automobiles | |
Letellier et al. | Acoustic properties of model cellular vitreous carbon foams | |
CN110110437A (en) | It is a kind of based on related interval indetermination theory automobile high-frequency noise prediction technique | |
Mosanenzadeh et al. | A numerical scheme for investigating the effect of bimodal structure on acoustic behavior of polylactide foams | |
Di Giulio et al. | Acoustic and thermoacoustic properties of an additive manufactured lattice structure | |
CN109933933B (en) | Noise treatment method and equipment | |
Bécot et al. | Applications of the dual porosity theory to irregularly shaped porous materials | |
Liu et al. | Development of an acoustic material database for vehicle interior trims | |
Wang et al. | Multi-stage regression analysis of acoustical properties of polyurethane foams | |
Boeckx et al. | A numerical scheme for investigating the influence of the three dimensional geometrical features of porous polymeric foam on its sound absorbing behavior | |
Nennig et al. | A homogenization method used to predict the performance of silencers containing parallel splitters | |
Sancak | An Investigations of Sound Absorbance Properties of Weft Knitted Spacer Fabrics. | |
Wu et al. | Optimization of acoustic performance of a vehicle dash sound package | |
Bécot et al. | Predicting alpha cabin sound absorption in an industrial context | |
Yang et al. | Acoustic study on the thermal aging of sound-absorbing polyurethane foam | |
Liu et al. | Determination of effective parameters of acoustic fabrics including sensitivity study | |
Sadouki et al. | Characterization of rigid porous medium via ultrasonic reflected waves at oblique incidence | |
Yang et al. | Application of acoustical method to characterize nonwoven material | |
CN112966804A (en) | Method and system for predicting foam copper sound absorption coefficient based on GRNN neural network optimization balance algorithm | |
CN112908433A (en) | Method for calculating sound absorption coefficient of double-layer composite structure open-cell foamed aluminum based on dimensional analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201222 |