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

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