This paper proposes a new method for leak localization in water distribution networks (WDNs). In a first stage, residuals are obtained by comparing pressure measurements with the estimations provided by a WDN model. In a second stage, a classifier is applied to the residuals with the aim of determining the leak location. The classifier is trained with data generated by simulation of the WDN under different leak scenarios and uncertainty conditions. The proposed method is tested both using synthetic and experimental data with real WDNs of different sizes. The comparison with the current existing approaches shows a performance improvement.

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

In this paper, the problem of robust fault diagnosis of proton exchange mem- ments lie inside their corresponding estimated interval bounds. When a fault is detected, the measurements that are inconsistent with their corresponding estimations are annotated and a fault isolation procedure is triggered. By using the theoretical fault signature matrix (FSM), which summarizes the effects of the different faults on the available residuals, the fault is isolated by means of a logic reasoning that takes into account the bounded uncertainty, and if the number of candidate faults is more than one, a correlation analysis is used to obtain the most likely fault candidate. Finally, the proposed approach is tested using a PEM fuel cell case study proposed in the literature.

This paper presents a new data-driven method for leak localization in water distribution networks. The proposed method relies on the use of available pressure measurements in some selected internal network nodes and on the estimation of the pressure at the remaining nodes using Kriging spatial interpolation. Online leak localization is attained by comparing current pressure values with their reference values. Supported by Kriging; this comparison can be performed for all the network nodes, not only for those equipped with pressure sensors. On the one hand, reference pressure values in all nodes are obtained by applying Kriging to measurement data previously recorded under network operation without leaks. On the other hand, current pressure values at all nodes are obtained by applying Kriging to the current measured pressure values. The node that presents the maximum difference (residual) between current and reference pressure values is proposed as a leaky node candidate. Thereafter, a time horizon computation based on Bayesian reasoning is applied to consider the residual time evolution, resulting in an improved leak localization accuracy. As a data-driven approach, the proposed method does not need a hydraulic model; only historical data from normal operation is required. This is an advantage with respect to most data-driven methods that need historical data for the considered leak scenarios. Since, in practice, the obtained leak localization results will strongly depend on the number of available pressure measurements and their location, an optimal sensor placement procedure is also proposed in the paper. Three different case studies illustrate the performance of the proposed methodologies.

This paper presents a sensor placement approach for classier-based leak localization in water distribution networks. The proposed method is based on a hybrid feature selection algorithm that combines the use of a lter based on relevancy and redundancy with a wrapper based on genetic algorithms. This algorithm is applied to data generated by hydraulic simulation of the considered water distribution network and it determines the optimal location of a prespecied number of pressure sensors to be used by a leak localization method based on pressure models and classiers proposed in previous works by the authors. The method is applied to a small-size simplied network (Hanoi) to better analyze its computational performance and to a mediumsize network (Limassol) to demonstrate its applicability to larger real-size networks.