Pipeline Leak Localization Using Pattern Recognition and a Bayes Detector

A novel leak localization method for multi section pipelines is presented. Based on normal operation flowing thermodynamic pressure drop patterns along the pipeline, the system continuously compares with the measured pressure drops, and makes a decision based on the best fit finding the section where the leak occurs. A statistical approach is used accounting for noisy measured signals. The method uses steady state fluid equations, a recursive parameter estimation algorithm, and statistical decision and pattern recognition techniques. A modification is introduced to consider the cost of making a wrong leaky section choice in terms of the excess volume spilled due to gravitational flow after pipeline shut down. This leads to a Bayesian decision scheme minimizing a risk functional. The costs are the spill volumes, obtained from dynamical simulation of the pipeline, under the various possible decision scenarios. Finally, details are given of the successful implementation of the system on a 500km long oil pipeline, and real data from a simulated leak experiment are shown.