Leak localization in water distribution networks using Bayesian classifiers. (July 2017)

• Record Type: Journal Article
• Authors: Soldevila, Adrià; Fernandez-Canti, Rosa M.; Blesa, Joaquim; Tornil-Sin, Sebastian; Puig, Vicenç
• Is Part Of: Journal of process control. Volume 55(2017)
• Page Start: 1
• Page End: 9
• Publication Date: 2017-07
• Subjects: Fault diagnosis -- Bayesian classifier -- Water distribution networks -- Leak localization; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2017.03.015
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract : Highlights: The Bayesian classifier is used to perform leak location. Pressure residuals are used as inputs to the classifier. The PDFs for each faulty class are created from data obtained using models. The proposed method is comparted with established methods. Abstract: 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.