Utilising pattern recognition techniques to implement a multipoint optical fibre sensor system for use in process water systems

Author

King, Damien ; Lyons, William B. ; Flanagan, Colin ; Lewis, Elfed

Author_Institution

Dept. of Electron. & Comput. Eng., Limerick Univ.

fYear

2005

fDate

Oct. 30 2005-Nov. 3 2005

Abstract

A multipoint optical fibre sensor system, containing five sensing elements, capable of detecting various concentrations of ethanol in water supplies is reported. The sensing elements are based on a U-bend sensor configuration and are incorporated into a 62.5mum core diameter 500-metre length of silica cladding silica core optical fibre. The sensor is interrogated using optical time domain reflectometry (OTDR) and it is proposed to apply artificial neural network (ANN) pattern recognition techniques to the resulting OTDR signals to accurately classify the sensor test conditions

Keywords

chemical sensors; fibre optic sensors; neural nets; optical time-domain reflectometry; pattern recognition; water supply; 500 m; 62.5 micron; U-bend sensor configuration; artificial neural network; ethanol; multipoint optical fibre sensor system; optical time domain reflectometry; pattern recognition; process water systems; silica core; water supplies; Artificial neural networks; Ethanol; Optical computing; Optical fiber networks; Optical fiber sensors; Optical fibers; Optical sensors; Pattern recognition; Reflectometry; Silicon compounds;

fLanguage

English

Publisher

ieee

Conference_Titel

Sensors, 2005 IEEE

Conference_Location

Irvine, CA

Print_ISBN

0-7803-9056-3

Type

conf

DOI

10.1109/ICSENS.2005.1597673

Filename

1597673