Radial-basis function network for the approximation of quasi-distributed FBG sensor spectra with distorted peaks

Aleksander S. Paterno; Lucia Valeria R. Arruda; Hypolito Jose Kalinowski

doi:10.1117/12.623814

23 May 2005 Radial-basis function network for the approximation of quasi-distributed FBG sensor spectra with distorted peaks

Aleksander S. Paterno, Lucia Valeria R. Arruda, Hypolito Jose Kalinowski

Author Affiliations +

Proceedings Volume 5855, 17th International Conference on Optical Fibre Sensors; (2005) https://doi.org/10.1117/12.623814
Event: 17th International Conference on Optical Fibre Sensors, 2005, Bruges, Belgium

Abstract

This paper describes the use of a neural network, specifically a Radial-Basis function network, to approximate spectra of the signal reflected by a fibre Bragg grating sensor. This approximation will help the interpretation of the data acquired from the sensor when it is supposed to work in a quasi-distributed way, but its reflected spectrum has non-uniformities which would cause the misinterpretation of the data if quasi-distributed demodulation techniques are used. Results using an emulated double-peaked spectrum from a fibre Bragg grating sensor show that the common practice of fitting with a gaussian curve and then finding its peak or directly finding the maximum of the raw spectrum would cause a larger error if compared to finding the peak of an approximated spectrum using the RBF network.

Citation Download Citation

Aleksander S. Paterno, Lucia Valeria R. Arruda, and Hypolito Jose Kalinowski "Radial-basis function network for the approximation of quasi-distributed FBG sensor spectra with distorted peaks", Proc. SPIE 5855, 17th International Conference on Optical Fibre Sensors, (23 May 2005); https://doi.org/10.1117/12.623814

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available