Publication
Data-driven leak localization in water distribution networks via dictionary learning and graph-based interpolation
Conference Article
Conference
IEEE Conference on Control Technology and Applications (CCTA)
Edition
6th
Pages
1265-1270
Doc link
https://doi.org/10.1109/CCTA49430.2022.9966160
File
Abstract
In this paper, we propose a data-driven leak localization method for water distribution networks (WDNs) which combines two complementary approaches: graph-based interpolation and dictionary classification. The former estimates the complete WDN hydraulic state (i.e., hydraulic heads) from real measurements at certain nodes and the network graph. Then, we append to the actual measurements a subset of relevant estimated states to feed and train the dictionary learning scheme. Thus, the meshing of these two methods is explored, and several promising performance results are attained, even deriving different mechanisms to increase the resilience to classical issues (e.g., dimensionality, interpolation errors, etc.). The approach is validated using the L-TOWN benchmark proposed in the BattLeDIM2020 competition.
Categories
learning (artificial intelligence), mathematical programming, optimisation.
Author keywords
Location awareness, interpolation, dictionaries, soft sensors, fitting, machine learning, distribution networks
Scientific reference
P. Irofti, L. Romero, F. Stoican and V. Puig. Data-driven leak localization in water distribution networks via dictionary learning and graph-based interpolation, 6th IEEE Conference on Control Technology and Applications, 2022, Milan, Italy, pp. 1265-1270.
Follow us!