A multi-point optical fibre sensor for condition monitoring in process water systems based on pattern recognition

Abstract

Preliminary results are presented for a multi-point optical fibre sensor designed to detect the presence of chemical species in water at spatial intervals of greater than 20 m. The sensor is addressed using optical time domain reflectometry (OTDR) with a spatial resolution of 10 m. The optical signals arising from the OTDR are highly complex due to interfering effects from external parameters such as localised fibre straining and temperature changes. Because of this level of complexity it has been found advantageous to use artificial neural networks (ANNs) as classifiers on the OTDR signals. The preliminary system has been trained initially to recognise only the presence of water, although it is planned to extend this capability to recognise the presence of contaminants in the water such as bacteria and chemical pollutants. Initial investigations show that different contaminants and interfering parameters (cross-sensitivities) may give rise to characteristic signatures on the OTDR signal which may be identified by the pattern recognition software.