IRI - Learning dictionaries from physical-based interpolation for water network leak localization

Publication

Learning dictionaries from physical-based interpolation for water network leak localization

Journal Article (2023)

Journal

IEEE Transactions on Control Systems Technology

Pages

755-766

Volume

Number

Doc link

http://doi.org/10.1109/TCST.2023.3329696

File

Download the digital copy of the doc pdf document

Authors

Irofti, Paul
Romero Ben, Luis
Stoican, Florin
Puig Cayuela, Vicenç

Projects associated

L-BEST: Supervision and fault-tolerant control of smart infrastructures based on advanced learning and optimization

Abstract

This article presents a leak localization methodology based on state estimation and learning. The first is handled by an interpolation scheme, whereas dictionary learning (DL) is considered for the second stage. The novel proposed interpolation technique exploits the physics of the interconnections between hydraulic heads of neighboring nodes in water distribution networks (WDNs). In addition, residuals are directly interpolated instead of hydraulic head values. The results of applying the proposed method to a well-known case study (Modena) demonstrated the improvements of the new interpolation method with respect to a state-of-the-art approach, both in terms of interpolation error (considering state and residual estimation) and posterior localization.

Author keywords

Dictionary learning, interpolation, leak localization, state estimation, water distribution network

Scientific reference

P. Irofti, L. Romero, F. Stoican and V. Puig. Learning dictionaries from physical-based interpolation for water network leak localization. IEEE Transactions on Control Systems Technology, 32(3): 755-766, 2023.