Simultaneous Detectability of Process and Sensor Faults: Application to Water Distribution Networks

TL;DR

This paper addresses the challenge of detecting leaks in Water Distribution Networks despite sensor faults by modeling the network as a graph and deriving theoretical detectability conditions, validated on real data.

Contribution

It introduces a graph-based modeling approach for WDNs with sensor and process faults and provides new theoretical results on their joint detectability.

Findings

Theoretical conditions for simultaneous detectability of faults in WDNs.

Validation of detectability results on real rural water network data.

Enhanced leak detection capability under sensor fault conditions.

Abstract

Detecting leaks in Water Distribution Networks (WDN) using sensors has become crucial towards an efficient management of water resources. The leak detection methods that use this data rely on the correctness of the acquired data. However, this assumption is often violated in practice. Consequently, leak detection under sensor faults is a problem of practical importance. This relates to the more general problem of simultaneous detectability in sensor and process faults for a class of systems modelled as a network, by exploiting the redundancies available through the topological relationship between the sensors. This paper hence aims at i) modeling WDN as graphs containing both systems and sensors faults ii) providing theoretical joint detectability results for such graphs and iii) applying these results to the scenario of leak identification under sensor faults conditions on real data issued from a rural WDN.