Optical reflectometric gas sensing: classification of hydrocarbon vapours by pattern recognition applied to RIfS sensor signals

Hydrocarbon vapours in air are monitored by a fibre-optical sensor system based on reflectometric interference spectroscopy (RIfS). A short review of the transducer principle and its properties is given. Classification of binary mixtures of hydrocarbon vapours is achieved by pattern recognition methods. The performance of principal component analysis and cluster analysis are compared to supervised and unsupervised artificial neural networks (self-organizing feature maps and back-propagation neural networks) for the evaluation of data from six RIfS sensors with respect to qualitative analysis.