Unsupervised Online Detection of Pipe Blockages and Leakages in Water Distribution Networks

2025-08-22

AI Summary

Addressing the challenge of online detection of pipe blockages (collective anomalies) and background leakage (concept drift) in water distribution networks, this paper proposes an unsupervised LSTM-VAE framework. It models temporal dynamics via sliding-window reconstruction error and integrates a dual drift detection mechanism to enable adaptive, real-time monitoring under non-stationary, label-free conditions. Innovatively, this work is the first to formally characterize pipe blockages as collective anomalies and background leakage as concept drift, and designs a lightweight, edge-deployable architecture. Experiments on two real-world water network datasets demonstrate that the method significantly outperforms state-of-the-art baselines in detection accuracy, robustness to recurrent drifts, and computational efficiency.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Time-Series/Data Streams
• Search and Optimization: Distributed Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Water Distribution Networks (WDNs), critical to public well-being and economic stability, face challenges such as pipe blockages and background leakages, exacerbated by operational constraints such as data non-stationarity and limited labeled data. This paper proposes an unsupervised, online learning framework that aims to detect two types of faults in WDNs: pipe blockages, modeled as collective anomalies, and background leakages, modeled as concept drift. Our approach combines a Long Short-Term Memory Variational Autoencoder (LSTM-VAE) with a dual drift detection mechanism, enabling robust detection and adaptation under non-stationary conditions. Its lightweight, memory-efficient design enables real-time, edge-level monitoring. Experiments on two realistic WDNs show that the proposed approach consistently outperforms strong baselines in detecting anomalies and adapting to recurrent drift, demonstrating its effectiveness in unsupervised event detection for dynamic WDN environments.

Problem

• Detects pipe blockages and leakages in water networks
• Addresses data non-stationarity and limited labeled data
• Enables real-time edge monitoring under dynamic conditions

Innovation

• LSTM-VAE for anomaly detection
• Dual drift detection mechanism
• Lightweight edge-level monitoring