Local resonance-type broadband acoustic metamaterial based on machine learning and application device thereof

An acoustic metamaterial and machine learning technology, applied in instruments, sound-generating instruments, etc., to achieve the effect of acoustic focusing and increasing transmittance

Active Publication Date: 2020-05-05
TSINGHUA UNIV
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present application provides a local resonance type broadband acoustic metamaterial and its application device based on machine learning. The acoustic wave frequency range of the acoustic metamaterial applied in the present invention is about (2000Hz-5000Hz), which solves the problem that is difficult to actively use in the prior art. Problems of regulating and protecting sound waves in a wide frequency range

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Local resonance-type broadband acoustic metamaterial based on machine learning and application device thereof
  • Local resonance-type broadband acoustic metamaterial based on machine learning and application device thereof
  • Local resonance-type broadband acoustic metamaterial based on machine learning and application device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] In this application, the acoustic metamaterial is applied to acoustic protection. The machine learning program debugging process of this embodiment is as follows:

[0060] Use frequency sweeps from 2000-5000Hz and random combinations of frequencies from 2000-5000Hz as simulation data to input into the machine learning program, and make a total of 100,000 sets of sound source data as simulation data. The machine learning program is interactively designed with COMSOL software. For each set of sound source data, the machine learning program will first use Fourier transform to process the sound source data to obtain the corresponding frequency band information as an input parameter and pass it into the machine learning program. Secondly, its intelligent Input a series of driving parameters of the micro motor and debugging parameters of the resistance wire. Among them, the motor driving parameters of the micro motor correspond to the driving distance to realize the length tha...

Embodiment 2

[0068] In this application, the acoustic metamaterial is applied to acoustic focusing. The machine learning program debugging process of this embodiment is as follows:

[0069] Use frequency sweeps from 2000-5000Hz and random combinations of frequencies from 2000-5000Hz as simulation data to input into the machine learning program, and make a total of 100,000 sets of sound source data as simulation data. The machine learning program is interactively designed with COMSOL software. For each set of sound source data, the machine learning program will first use Fourier transform to process the sound source data to obtain the corresponding frequency band information as an input parameter and pass it into the machine learning program. Secondly, its intelligent Input a series of driving parameters of the micro motor and debugging parameters of the resistance wire. Among them, the motor driving parameters of the micro motor correspond to the driving distance to realize the length that ...

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

No PUM Login to View More

Abstract

The invention provides a local resonance-type broadband acoustic metamaterial based on machine learning and an application device thereof, which belong to the field of acoustics, and is used for solving the problem that active regulation and control for acoustic wave signals of different frequency bands cannot be realized in the prior art, so that acoustic wave regulation and control in a broadband range is difficult to realize. The acoustic meta-material comprises: a hollow pipe with an adjustable length, and a hollow ball with an adjustable opening size. The hollow pipe is made of steel materials, the length of the hollow pipe is controlled through a micro motor to adjust the resonant frequency, the hollow ball is made of shape memory alloy and placed on a grid structure made of epoxy resin, and the opening size of the hollow ball is controlled through the temperature to adjust the resonant frequency. The software simulation is utilized to enable a machine learning program to learn to obtain an optimal structural form of the metamaterial for acoustic wave protection of different frequency bands, and finally active regulation and control and protection for specific broadband acoustic waves (2000-5000Hz) are achieved.

Description

technical field [0001] This application relates to the field of functional materials, in particular to local resonance broadband acoustic metamaterials based on machine learning and their application devices. Background technique [0002] At present, the types of acoustic metamaterials are roughly divided into two types, local resonance type and curled space type. Whether it is local resonance or curled space, most of the existing acoustic metamaterials can only achieve negative equivalent mass density or negative equivalent elastic modulus corresponding to specific characteristic frequencies, and cannot achieve active regulation for signals in different frequency bands, so it is difficult Realize wide frequency range of sound wave regulation. Contents of the invention [0003] The embodiment of the present application provides a local resonance type broadband acoustic metamaterial and its application device based on machine learning. The acoustic wave frequency range of ...

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
no application Login to View More
IPC IPC(8): G10K11/162
CPCG10K11/162
Inventor施汇斌杜智博柳占立庄茁
OwnerTSINGHUA UNIV