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

摘要

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 62.5/spl mu/m 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.