Interrogation system for optical sensor using filter bank and artificial neural network

Abstract

AbstractConsidering the increasingly wide application of optical fiber sensors, this article aims to present an alternative form of interrogation without the use of an optical spectrum analyzer or any other high‐cost devices. The sensor studied here is a long‐period grating being used to measure temperature. The interrogator is composed of optical filters and photodetectors whose responses are processed by a suitably trained artificial neural network. Results show that this technique enables effective interrogation of a range limited only by the optical bandwidth of the light source.