Enhanced Water Leak Detection with Convolutional Neural Networks and One-Class Support Vector Machine

TL;DR

This paper introduces a novel water leak detection method combining CNN-based feature extraction with one-class SVMs, leveraging pressure data and network topology to improve detection accuracy in water distribution systems.

Contribution

It presents a fully data-driven leak detection approach using pressure measurements and one-class SVMs trained on no-leak data, outperforming recent methods.

Findings

Outperforms recent leak detection methods on simulated data

Effective in identifying leaks as anomalies using pressure data

Utilizes only topology and pressure data, no additional sensors

Abstract

Water is a critical resource that must be managed efficiently. However, a substantial amount of water is lost each year due to leaks in Water Distribution Networks (WDNs). This underscores the need for reliable and effective leak detection and localization systems. In recent years, various solutions have been proposed, with data-driven approaches gaining increasing attention due to their superior performance. In this paper, we propose a new method for leak detection. The method is based on water pressure measurements acquired at a series of nodes of a WDN. Our technique is a fully data-driven solution that makes only use of the knowledge of the WDN topology, and a series of pressure data acquisitions obtained in absence of leaks. The proposed solution is based on an feature extractor and a one-class Support Vector Machines (SVM) trained on no-leak data, so that leaks are detected as anomalies. The results achieved on a simulate dataset using the Modena WDN demonstrate that the proposed solution outperforms recent methods for leak detection.