Detecting Leaks in Water Distribution Pipes Using a Deep Autoencoder and Hydroacoustic Spectrograms

TLDR

Small leaks in buried water pipelines remain undetected because their pressure impact is imperceptible, a problem compounded by leak size and demand variability, and deep learning offers a better way to separate these effects than traditional heuristics. This study applies deep learning to acoustic monitoring data to detect leaks in water distribution networks. A semi‑supervised method combines a convolutional neural network with a variational autoencoder to flag anomalies in a laboratory test bed linked to a municipal water system, using typical operating conditions as the baseline. The approach achieved 97.2 % accuracy in detecting a 0.25 L/s leak, proving the deep autoencoder’s effectiveness for leak detection in WDNs.

Abstract

Small leaks in buried water distribution pipelines typically remain undetected indefinitely because the impact small leaks have on the overall system pressure is imperceptible. This difficulty is caused by a combination of the leak’s magnitude and the demand variability within water distribution networks (WDNs). Deep learning has the potential to disentangle these sources of variability more capably than traditional heuristics. This paper applies deep learning to acoustic monitoring data to detect leaks. Due to the lack of leak data in practice, a semisupervised approach was proposed. In this approach, a convolutional neural network is combined with a variational autoencoder to detect anomalies in a laboratory test bed. The test bed used is connected to the municipal water system via a service line, thus ensuring realistic baseline variation. The baseline case is defined by the test bed’s typical operating conditions when no leak is present. The proposed method achieved an accuracy of 97.2% for detecting a 0.25 L/s leak, demonstrating the effectiveness of the deep autoencoder for leak detection in WDNs.