Share Email Print
cover

Proceedings Paper

Self-learning structural identification algorithm
Author(s): Tadanobu Sato; Makoto Sato
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper deals with the identification of the dynamic characteristics of structural system. The relevant neural network characteristics of learning algorithm are discussed in the context of system identification. Because of self-learning nature of neural network the identified dynamic characteristics are strongly affected by the level of noise contained in the teaching signals. Using the Kalman filtering technique, a method to identify the dynamic characteristics of structural system proof against contaminating noise in teaching signals has been developed.

Paper Details

Date Published: 8 May 1995
PDF: 8 pages
Proc. SPIE 2443, Smart Structures and Materials 1995: Smart Structures and Integrated Systems, (8 May 1995); doi: 10.1117/12.208287
Show Author Affiliations
Tadanobu Sato, Kyoto Univ. (Japan)
Makoto Sato, Kyoto Univ. (Japan)


Published in SPIE Proceedings Vol. 2443:
Smart Structures and Materials 1995: Smart Structures and Integrated Systems
Inderjit Chopra, Editor(s)

© SPIE. Terms of Use
Back to Top