Sound emission signal denoising method based on denoising autoencoder

An acoustic emission signal and autoencoder technology, applied in the field of signal processing

Pending Publication Date: 2021-06-08
CHONGQING BUSINESS VOCATIONAL COLLEGE
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In actual engineering measurement, it is a typical nonlinear pattern recognition problem to analyze the collected AE signal to infer the type and degree of defec

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
  • Sound emission signal denoising method based on denoising autoencoder
  • Sound emission signal denoising method based on denoising autoencoder
  • Sound emission signal denoising method based on denoising autoencoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0075] 1. Calculation examples

[0076] (1) Determination of the number of neurons in the hidden layer of DAE

[0077] DAE is a neural network with a single hidden layer structure, and the number of neurons in the hidden layer needs to be set according to the actual denoising application scenarios of DAE. Here, the signal-to-noise ratio is used to measure the denoising performance, as shown in formula (10):

[0078]

[0079] Among them, P signal , P noise are the power of signal and noise, respectively; and P signal to attach Figure 5 The normalized corrosion AE signal power shown, P noise is the acoustic emission signal power after denoising and P signal Difference.

[0080] The DAE encoding activation function selects the Logistic sigmoid function, the decoding activation function selects the Positive saturating linear transfer function, and the loss function adopts the mean square error function MSE (Mean SquaredError), as shown in formula (11):

[0081]

[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 discloses a sound emission signal denoising method based on a denoising autoencoder (DAE), which is characterized in that the denoising autoencoder is trained through unsupervised learning to learn more stable invariance features, so that the error between a reconstructed signal and an original signal is converged to a minimum value, and the denoising purpose is achieved. A denoising experiment is carried out on the basis of processing 3011 corrosion sound emission signal samples; the experiment result shows that when the number of hidden layer neurons is 300, the denoising model has a good denoising effect, and the denoising model of the denoising autoencoder has better denoising performance and generalization compared with a wavelet threshold denoising method. The denoising autoencoder denoising model is applied to sound emission signal denoising, can effectively remove noise, and is of great significance to subsequent sound emission signal recognition processing.

Description

technical field [0001] The invention belongs to the technical field of signal processing, and in particular relates to an acoustic emission signal denoising method based on a denoising self-encoder. Background technique [0002] When the material is subjected to external force or internal force to produce deformation or crack expansion, the phenomenon of releasing strain energy in the form of elastic waves is called acoustic emission. The technology of detecting and analyzing acoustic emission signals with instruments and using acoustic emission signals to infer the source of acoustic emission is called acoustic emission detection technology. Acoustic emission testing technology is different from conventional non-destructive testing methods. It is a passive dynamic testing method that does not need to enter the test object for testing, and has unique advantages such as real-time, integrity and high sensitivity, and can dynamically monitor the health of structures. [0003] ...

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): G06K9/00G06N3/04
CPCG06N3/045G06F2218/04
Inventor 周俊刘凡漪
Owner CHONGQING BUSINESS VOCATIONAL COLLEGE
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap