Utilisation of pattern recognition techniques to interpret complex data from a multipoint optical fibre ethanol concentration sensor system

A multipoint optical fibre sensor system, capable of detecting various concentrations of ethanol in water is reported. The sensor system is based on a 500 m length of 62.5 μm diameter core silica clad silica core optical fibre and includes five sensing elements located along the fibre length. The sensing elements are based on evanescent wave absorption sensors and each sensor utilises a U-bend sensor configuration in order to maximise its sensitivity. The sensor system is interrogated using a technique known as optical time domain reflectometry, as this method is capable of measuring attenuation as a function of distance. Analysis of the data arising from the sensor system is performed using artificial neural network pattern recognition techniques, coupled with discrete Fourier transform-based signal processing. The signal processing techniques are applied to the obtained sensor system data, prior to the artificial neural network analysis, with the aim of reducing the computational resources required by the implemented artificial neural network in software.