-
Blind separation of independent acoustic emission sourcesKosel, Tadej ; Grabec, IgorOne non-destructive testing method is acoustic emission analysis, which is used for the characterisation and location of acoustic emission sources. Acoustic emission sources are often a mixture of ... various statistically independent source signals generated in a material. One of the most difficult problems of acoustic emission analysis is the separation and characterisation of the independent acoustic emission sources without knowing source signals and the mixing function. Both the source signals and the way the signals were mixed are unknown. Recently, Blind Source Separation (BSS) by Independent Component Analysis (ICA) has been the focus of attention to solve these problems. Independent Component Analysis is based on neural networks and uses minimisation of mutual information for the cost function. There are two variations of this method. The first deals with the instantaneous mixtures and the second with the convolutive mixtures of the independent sources. The main purpose of this work is to determine if independent component analysis is also useful for separation of independent acoustic emission sources and if it is possible to locate separate sources in laboratory specimens using an adaptive locator which is based on non-parametric regression. Some computer simulated and real experiments were performed on two test specimens and with several different acoustic emission sources. It was found that independent components analysis can be used to separate the independent acoustic emission sources with some limitations which are valid for this kind of method. A negative influence on blind source separation is also exerted by dispersion of acoustic waves, which is a property of the waveguides e.g. plates and ribbons. The majority of acoustic emission test specimens have such properties. It was also found that, with independent component analysis which uses convolutive mixtures, it is possible to locate independent acoustic emission sources.Source: Abstract book (Paper E1.05)Type of material - conference contribution ; adult, seriousPublish date - 2001Language - englishCOBISS.SI-ID - 4476699
Author
Kosel, Tadej |
Grabec, Igor
Topics
metode preskušanja |
metode neporušne |
analize AE |
karakterizacija |
izvori AE |
non-destructive testing |
acoustic emission |
neural networks |
source location |
adaptive locator |
non-parametric regression |
acoustic emission sources |
BSS |
blind source separation |
ICA |
independent components analysis |
mutual information |
waveguides |
dispersion waves
![loading ... loading ...](themes/default/img/ajax-loading.gif)
Shelf entry
Permalink
- URL:
Impact factor
Access to the JCR database is permitted only to users from Slovenia. Your current IP address is not on the list of IP addresses with access permission, and authentication with the relevant AAI accout is required.
Year | Impact factor | Edition | Category | Classification | ||||
---|---|---|---|---|---|---|---|---|
JCR | SNIP | JCR | SNIP | JCR | SNIP | JCR | SNIP |
Select the library membership card:
DRS, in which the journal is indexed
Database name | Field | Year |
---|
Links to authors' personal bibliographies | Links to information on researchers in the SICRIS system |
---|---|
Kosel, Tadej | 15696 |
Grabec, Igor | 00800 |
Select pickup location:
Material pickup by post
Notification
Subject headings in COBISS General List of Subject Headings
Select pickup location
Pickup location | Material status | Reservation |
---|
Please wait a moment.