A neural networks based approach for determining fouling of multi-point optical fibre sensors in water systems

An optical fibre sensor system for monitoring contamination in water suppli es is presented. The sensor comprises a number of individual sensor element s on a single fibre loop. It is addressed using optical time domain reflect ometry so that the required spatial resolution of 1 metre is achieved. Anal ysis of the signals at the receiving end is performed using artificial neur al networks coupled with pattern recognition techniques, thus allowing exte rnal influences such as the degree of sensor fouling to be detected. In thi s investigation limescale build-up in hard water is investigated as the int erfering parameter.