This paper presents a method for leak localization in water distribution networks (WDNs) based on Bayesian classifiers. Probability density functions for pressure residuals are calibrated off-line for all the possible leak scenarios by using a hydraulic simulator, and considering the leak size uncertainty, demand uncertainty and sensor noise. A Bayesian classifier is applied on-line to the computed residuals to determine the location of leaks in the WDN. A time horizon based reasoning combined with the Bayesian classifier is also proposed to improve the localization accuracy. Two case studies based on the Hanoi and the Nova Icària networks are used to illustrate the performance of the proposed approach. Simulation results are presented for the Hanoi case study, whereas results for a real leak scenario are shown for the Nova Icària case study.Peer ReviewedPostprint (author's final draft

SUMMARY: In this paper, robust fault detection based on adaptive threshold generation of a non‐linear system described by means of a linear parameter‐varying (LPV) model is addressed. Adaptive threshold is generated using an interval LPV observer that generates a band of predicted outputs taking into account the parameter uncertainties bounded using intervals. An algorithm that propagates the uncertainty based on zonotopes is proposed. The design procedure of this interval LPV observer is implemented via pole placement using linear matrix inequalities. Finally, the minimum detectable fault is characterized using fault sensitivity analysis and residual uncertainty bounds. Two examples, one based on a quadruple‐tank system and another based on a two‐degree of freedom helicopter, are used to assess the validity of the proposed fault detection approach. Copyright © 2011 John Wiley & Sons, Ltd.