SIMULTANEOUS LEAK DETECTION WITH MAGNITUDE AT TWO POSITIONS FOR FLOW OF WATER IN PIPELINE USING ARTIFICIAL NEURAL NETWORK

Chemical process industries have complex structures comprising of equipments & network of pipelines carrying volatile, flammable & hazardous fluids. The timely detection of leak position & its magnitude is one of the challenging tasks. The present work is aimed at leak detection in a pipeline using artificial neural network models. Experimental runs are conducted & pressure drop for flow of water across the orifice meters placed in five sections is measured for normal conditions & with leak in one or two sections with varying magnitude. Part of the experimental data is used for developing two ANN models S & C having different topology. The validation is carried out using test data set. The trained networks are used for the prediction of these leak parameters. Based on the comparisons of the actual & predicted values of all the output parameters, it can be said that the present work is successful in developing models having high accuracy