Share Email Print

Proceedings Paper

Optimization of training sets for neural-net processing of characteristic patterns from vibrating solids
Author(s): Arthur J. Decker
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Artificial neural networks have been used for a number of years to process holography-generated characteristic patterns of vibrating structures. This technology depends critically on the selection and the conditioning of the training sets. A scaling operation called folding is discussed for conditioning training sets optimally for training feed-forward neural networks to process characteristic fringe patterns. Folding allows feed-forward nets to be trained easily to detect damage-induced vibration-displacement-distribution changes as small as 10 nanometers. A specific application to aerospace of neural-net processing of characteristic patterns is presented to motivate the conditioning and optimization effort.

Paper Details

Date Published: 26 November 2001
PDF: 9 pages
Proc. SPIE 4448, Optical Diagnostics for Fluids, Solids, and Combustion, (26 November 2001); doi: 10.1117/12.449379
Show Author Affiliations
Arthur J. Decker, NASA Glenn Research Ctr. (United States)

Published in SPIE Proceedings Vol. 4448:
Optical Diagnostics for Fluids, Solids, and Combustion
Carolyn R. Mercer; Soyoung Stephen Cha; Gongxin Shen, Editor(s)

© SPIE. Terms of Use
Back to Top