An artificial neural network approach for the prediction of absorption measurements of an evanescent field fiber sensor

Creative Commons License

Saracoglu O. G.

SENSORS, vol.8, no.3, pp.1585-1594, 2008 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 8 Issue: 3
  • Publication Date: 2008
  • Doi Number: 10.3390/s8031585
  • Journal Name: SENSORS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.1585-1594
  • Keywords: fiber optic sensor, evanescent field, absorption, artificial neural networks, RELATIVE-HUMIDITY SENSOR, OPTICAL-FIBER, SENSITIVITY, RANGE, DESIGN
  • Erciyes University Affiliated: Yes

Abstract

This paper describes artificial neural network ( ANN) based prediction of the response of a fiber optic sensor using evanescent field absorption (EFA). The sensing probe of the sensor is made up a bundle of five PCS fibers to maximize the interaction of evanescent field with the absorbing medium. Different backpropagation algorithms are used to train the multilayer perceptron ANN. The Levenberg-Marquardt algorithm, as well as the other algorithms used in this work successfully predicts the sensor responses.