IWSHM-2010
Описание
The paper is concerned with adopting a data-driven approach to damage detection and location on an aerospace structure without recourse to an artificial neural network. This is achieved via the selection of 'advanced features' which are only sensitive to damage at a particular location. These advanced features were selected by analysing discordancy values. Damage was detected for all of the damaged panels. Advanced features were selected for all 5 panels with 4 of the features showing promise.
Содержание
|
Регламенты
25 декабря 2013
09 января 2014
|