Acoustic Leak Detection in Water Networks

TL;DR

This paper introduces a general acoustic leak detection method for water networks that balances energy efficiency and deployment ease, utilizing anomaly detection models trained on microphone data to identify leaks over time.

Contribution

It presents a novel procedure combining shallow and deep anomaly detection models inspired by human leak detection techniques, optimized for real-world constraints.

Findings

Neural networks outperform shallow models in detecting distant leaks.

Detection of nearby leaks is straightforward for most models.

The approach reduces continuous monitoring needs.

Abstract

In this work, we present a general procedure for acoustic leak detection in water networks that satisfies multiple real-world constraints such as energy efficiency and ease of deployment. Based on recordings from seven contact microphones attached to the water supply network of a municipal suburb, we trained several shallow and deep anomaly detection models. Inspired by how human experts detect leaks using electronic sounding-sticks, we use these models to repeatedly listen for leaks over a predefined decision horizon. This way we avoid constant monitoring of the system. While we found the detection of leaks in close proximity to be a trivial task for almost all models, neural network based approaches achieve better results at the detection of distant leaks.