Publication

Leak localization method for water distribution networks using a data-driven model and Dempster-Shafer reasoning

Journal Article (2021)

Journal

IEEE Transactions on Control Systems Technology

Doc link

https://doi.org/10.1109/TCST.2020.2982349

File

Download the digital copy of the doc pdf document

Abstract

This paper presents a new data-driven method forleak localization in water distribution networks. The methoduses the information provided by a set of pressure sensorsinstalled in some internal network nodes in addition to flow andpressure measurements from inlet nodes. Pressure measurements are recorded under leak-free network operation and a water distribution network data-driven model of the pressure at each sensed node is adjusted. The pressure estimation from this model is complemented by a Kriging spatial interpolation technique to estimate pressure in the nodes which are not sensed, leading to a pressure reference map. Leak localization is based on the comparison of this reference pressure map with the current pressure map which is obtained by applying Kriging directly to the pressure measurements provided by sensors. The key element in this comparison is the use of Dempster-Shafer theory for reasoning under uncertainty. The successful application of the proposed methodology to two real-data case studies is presented.

Categories

control theory.

Author keywords

Pressure measurement, Hydraulic systems, Cognition, Pressure sensors, Water resources, Leak detection

Scientific reference

A. Soldevila, J. Blesa, T. Jensen, S. Tornil-Sin, R.M. Fernandez-Cantí and V. Puig. Leak localization method for water distribution networks using a data-driven model and Dempster-Shafer reasoning. IEEE Transactions on Control Systems Technology, 2021, to appear.