Localization of Acoustic Emission Sources by Means of Statistical Methods

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F03%3A00164596" target="_blank" >RIV/68407700:21340/03:00164596 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Localization of Acoustic Emission Sources by Means of Statistical Methods
Original language description
In this contribution we present and apply several statistical methods taken from the class of change point detection algorithms for given time series. Particularly, we consider CUSUM and chi^2 methods based on testing statistical hypotheses in the framework of autoregressive processes and further the method of singular spectral analysis (SSA). The SSA uses singular value decomposition of lag covariance matrix. Consequently, we consider retrospective Bayesian linear detector to obtain a posteriori probability density of the positions of abrupt changes in a given time series. The comparative analysis was produced in terms of the sample means and mean square errors (MSE) of the change point positions. Finally, the linear localization procedures were applied to the data originated from the laboratory tests on rail track and also to the real signals measured and sampled at the wing girder of a small aircraft.
Czech name
—
Czech description
—

Publication year
2003
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)