Parameter sound source modeling method based on improved BP (Back Propagation) neural network

A BP neural network and parametric sound source technology, which is applied in the field of parametric sound source modeling based on improved BP neural network, can solve the problems of taking into account scattering effects and difficulty in obtaining analytical solutions, shortening the convergence time and improving the accuracy of the model. The effect of high degree and model accuracy

Active Publication Date: 2013-05-01
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF2 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the "Berktay far-field solution" only takes the second-order approximation when considering nonlinear effects, and does not take into account effects such as scattering and absorption, it can only be used as a qualitative basis
Although the Khokhlov-Zabolotskaya-Kuznetsov (KZK) equation fully takes into account the nonlinearity, absorption, and scattering effects of the finite-amplitude sound beam in fluids and solids, it is still difficult to obtain the analytical solution of the equation

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
  • Parameter sound source modeling method based on improved BP (Back Propagation) neural network
  • Parameter sound source modeling method based on improved BP (Back Propagation) neural network
  • Parameter sound source modeling method based on improved BP (Back Propagation) neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The technical scheme of the present invention is described in detail below in conjunction with accompanying drawing:

[0028] The idea of ​​the invention is to use the artificial intelligence neural network improved by the genetic algorithm to construct the model of the parametric sound source. The process of establishing the model will be described in detail below.

[0029] Selection of input and output variables:

[0030] For the parametric sound source model established by the neural network, the input and output of the parametric sound source correspond to the input and output of the built model respectively. At the same time, in order to improve the accuracy of the model, the input of the parametric sound source should try to select a single-frequency signal, and the acquisition of the parameter The sampling rate of the output microphone of the sound source should satisfy the Nyquist sampling theorem. In the present invention, the sampling rate is 44.1Khz.

[00...

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 parameter sound source modeling method based on an improved BP (Back Propagation) neural network, in order to solve the problem of difficulty in modeling a parameter sound source system at present. The method comprises the following steps: firstly, collecting sufficient training and testing sample data and preprocessing the data; establishing a neural network model; adopting a genetic algorithm for performing optimizing process on the structure and parameter of the neural network model; searching for an initial weight value and a threshold value between the number of better neural network hidden layers and neural cells; and lastly, training and testing an established parameter sound source model based on the improved BP neural network by using the sample data. The model has the advantages of reliability and higher assessing precision.

Description

technical field [0001] A modeling method of a parametric sound source, in particular relates to a modeling method of a parametric sound source based on an improved BP neural network. Background technique [0002] The parametric sound source is a new concept sound source that uses the nonlinear propagation effect of ultrasonic waves to generate high-directional audio sound waves and has broad application prospects. However, since the working principle of the parametric loudspeaker is to use the nonlinear interaction of the air, the self-demodulated sound signal will inevitably be distorted, and the nonlinear distortion factor will inevitably be increased when the ultrasonic modulation is performed on the audible sound. Although now Using a better modulation algorithm, the distortion of the demodulated audible sound (sound distortion) has been greatly improved, but this sound distortion still exists in the actual audio frequency directional system. To solve the problem of sou...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/50G06N3/02G06N3/12
Inventor 陈敏杨天文陈祥靳银蕊杨亚洲
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products