Neural Networks and Optical Fibre Interrogating

Interrogating Signals from a Multipoint Optical Fibre Sensor System using Neural Network Techniques

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 62.5mm core diameter 500-metre length of silica cladding silica core optical fibre. The sensor system is interrogated at 850nm 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.