Method for predicting intermediate-frequency sound absorption coefficient of composite structure open-cell foamed aluminum based on neural network
A technology of open-cell foam aluminum and neural network, which is applied in the field of predicting the mid-frequency sound absorption coefficient of composite structure open-cell foam aluminum, can solve the problems of heavy workload and large error of test results, and achieve the goal of improving design efficiency and small error Effect
Pending Publication Date: 2020-12-22
XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
A single sound-absorbing material has been difficult to meet people's requirements for sound absorption and noise reduction. Therefore, the development and application of composite structures have attracted more and more attention. However, for the design of composite structures, most of them measure their sound absorption coefficients to obtain performance Relatively excellent parameter range of composite structures, but this method has a heavy workload and large error in test results, so there is an urgent need for a simple, fast and accurate prediction method for frequency sound absorption coefficient
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0044] The following is an illustration of the prediction case of the sound absorption coefficient at 500 Hz based on the designed composite structure:
[0045] Step 1: Measure the sound absorption coefficients of 20 composite structures at 500 Hz by using standing wave tubes, and the specific values are shown in Table 2;
[0046] Step 2: Use MATLAB to carry out sample definition (20 sets of samples) and sample division of the measured 20 sets of data, select samples from No. 1 to No. 15 as training samples, and samples from No. 16 to No. 20 as test samples;
[0047] Step 3: Determination of the smooth factor, the generalized regression neural network uses the Gaussian function as the basis function. The width coefficient of the Gaussian function, also known as the smoothing factor α, when the value of the smoothing factor α tends to zero, the prediction effect is poor, and when the value is too large, the predicted value is close to the average value of all sample dependent...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for predicting an intermediate-frequency sound absorption coefficient of of composite structure open-cell foamed aluminum based on a neural network. The method comprises the following steps: designing a double-layer composite structure; determining influence factors influencing the sound absorption capability of the open-cell foamed aluminum, determining sound absorption coefficients of multiple different composite structures under the influence factors and sound sources with different frequencies, and obtaining data sets corresponding to the influence factorsand the sound absorption coefficients of the multiple different composite structures; dividing the data set into a training sample and a test sample; using a newgrnn function of MATLAB to create a generalized regression neural network, and training and testing the generalized regression neural network through the training sample and the test sample to obtain a final generalized regression neural network; and during prediction, inputting the influence factors of a to-be-predicted composite structure into the final generalized regression neural network, and predicting the sound absorption coefficient of the composite structure. By means of the method, the sound absorption coefficient of the double-layer composite structure with the cavity can be rapidly predicted, and tedious experiments arenot needed for determination.
Description
technical field [0001] The method relates to the field of sound absorption and noise reduction, in particular to a neural network-based method for predicting the mid-frequency sound absorption coefficient of open-cell aluminum foam with a composite structure. Background technique [0002] At present, solving the problem of noise pollution is an urgent matter. The sound absorption principle of sound-absorbing materials or structures is mainly the principle of resonance sound absorption and the principle of porous sound absorption. A single sound-absorbing material has been difficult to meet people's requirements for sound absorption and noise reduction. Therefore, the development and application of composite structures have attracted more and more attention. However, for the design of composite structures, most of them measure their sound absorption coefficients to obtain performance Relatively excellent parameter range of composite structures, but this method has a heavy wo...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06F30/13G06N3/04G06F119/10
CPCG06F30/27G06F30/13G06N3/04G06F2119/10
Inventor 梁李斯郭文龙张宇米嘉毓
Owner XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY