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 $14.40 $18.00
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

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