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 supplies is presented. The sensor comprises a number of individual sensor elements on a single fibre loop. It is addressed using optical time domain reflectometry so that the required spatial resolution of 1 metre is achieved. Analysis of the signals at the receiving end is performed using artificial neural networks coupled with pattern recognition techniques, thus allowing external influences such as the degree of sensor fouling to be detected. In this investigation limescale build-up in hard water is investigated as the interfering parameter.