Share Email Print

Proceedings Paper

Smart integrated-optics displacement/force sensor based on speckle pattern detection using neural-net with 0.1-A resolution
Author(s): Umesh K. Rao; Augusto Garcia-Valenzuela; Massood Tabib-Azar
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper describes the usage of neural networks in the application of speckle patterns, as seen at the output of an optical waveguide, for sensing displacement/force. The neural network trained for displacement values within a 1.5 micrometers range is found to generalize with less than +/- 0.02 micrometers error in the input range. It is found that a functional-link net with 11 functional links and 3 neurons can be trained for a convergence criterion of 1e-05 in less than 3000 iterations. The error in the individual targeted output during training was less than +/- 0.01 micrometers . Thus an integrated-optics sensor is now feasible.

Paper Details

Date Published: 2 March 1993
PDF: 11 pages
Proc. SPIE 1793, Integrated Optics and Microstructures, (2 March 1993); doi: 10.1117/12.141229
Show Author Affiliations
Umesh K. Rao, Case Western Reserve Univ. (United States)
Augusto Garcia-Valenzuela, Case Western Reserve Univ. (United States)
Massood Tabib-Azar, Case Western Reserve Univ. (United States)

Published in SPIE Proceedings Vol. 1793:
Integrated Optics and Microstructures
Massood Tabib-Azar; Dennis L. Polla, Editor(s)

© SPIE. Terms of Use
Back to Top