Files
website/content/research/2021-03-03-acoustic-leak-detection.mdx
Steffen Illium 0444067c2d
Some checks failed
Next.js App CI / docker (push) Failing after 3m19s
refined design
2025-09-14 22:49:23 +02:00

35 lines
2.6 KiB
Plaintext

---
title: "Acoustic Leak Detection"
tags: [anomaly-detection, audio-processing, deep-learning, signal-processing, real-world-application, water-networks, infrastructure-monitoring]
excerpt: "Anomaly detection models for acoustic leak detection in water networks."
teaser: "/figures/10_water_networks_teaser.jpg"
venue: "ICAART 2021"
---
Detecting leaks in vast municipal water distribution networks is critical for resource conservation and infrastructure maintenance. This study introduces and evaluates an **anomaly detection approach for acoustic leak identification**, specifically designed with **energy efficiency** and **ease of deployment** as key considerations.
<FloatingImage
src="/figures/10_water_networks_approach.jpg"
alt="Diagram illustrating the anomaly detection approach for acoustic leak identification in water networks."
width={400}
height={300}
float="right"
caption="Illustration of the anomaly detection approach for acoustic leak identification in water networks."
/>
The methodology leverages acoustic recordings captured by microphones deployed directly on a section of a real-world **municipal water network**. Instead of requiring continuous monitoring, the proposed system mimics human inspection routines by performing **intermittent checks**, significantly reducing power consumption and data load.
Various **anomaly detection models**, ranging from traditional "shallow" methods (e.g., GMMs, OC-SVMs) to more complex **deep learning architectures** (e.g., autoencoders, potentially CNNs on spectrograms), were trained using data representing normal network operation. These models were then evaluated on their ability to distinguish anomalous sounds indicative of leaks.
Key findings include:
* Detecting leaks occurring acoustically **nearby** the sensor proved relatively straightforward for most evaluated models.
* **Neural network-based methods demonstrated superior performance** in identifying leaks originating **further away** from the sensor, showcasing their ability to capture more subtle acoustic signatures amidst background noise.
<CenteredImage
src="/figures/10_water_networks_mel.jpg"
alt="Mel-spectrogram examples showing acoustic signatures of normal operation versus leak sounds"
width={800}
height={400}
caption="Mel-spectrogram visualizations comparing normal sounds and leak-related acoustic patterns."
maxWidth="100%"
/>
This research validates the feasibility of using anomaly detection for practical, energy-efficient acoustic leak monitoring in water networks, highlighting the advantages of deep learning techniques for detecting more challenging, distant leaks. <Cite bibtexKey="muller2021acoustic" />