On feature extraction for condition monitoring using time series analysis and distance techniques

Citation
I. Trendafilova et al., On feature extraction for condition monitoring using time series analysis and distance techniques, INVERSE P E, 8(1), 2000, pp. 1-24
Citations number
19
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Engineering Mathematics
Journal title
INVERSE PROBLEMS IN ENGINEERING
ISSN journal
1068-2767 → ACNP
Volume
8
Issue
1
Year of publication
2000
Pages
1 - 24
Database
ISI
SICI code
1068-2767(2000)8:1<1:OFEFCM>2.0.ZU;2-P
Abstract
The paper comprises two parts which explore some possibilities for feature extraction and classification in condition monitoring of robot joints from their measured acceleration signatures. The symmetrized Itakura distance is used to form features and to develop several classifiers to distinguish be tween signals coming from joints with different amounts of backlash. The cl assifiers are tested and their performance is discussed and compared. In th e second part some nonlinear dynamics characteristics are extracted directl y from the measured transients and considered as possible features for defe ct detection and classification. Finally, the potential of nonlinear dynami cs for robot joint dynamics modeling is highlighted.