Acoustic localization approach for urban water distribution networks using machine learning method

Leakage in water pipelines causes the loss of valuable amounts of water and can result in considerable environmental damage. This study presents a real-time leak localization method using signal processing and machine learning (ML) techniques, addressing challenges in accuracy, cost, and real-world applicability. Firstly, a novel two-stage localization method is proposed, streamlining the traditional three-stage approach, for reducing cost and time by utilizing only noise loggers and correlators while maintaining effectiveness. To address the disparity between laboratory-based models and real-world applications, a real-life database is established in this study. This continuously updating database incorporates diverse real leak data scenarios from Hong Kong over a period exceeding one year, ensuring model accuracy and relevance in practical settings. Furthermore, various decomposition techniques are employed to extract relevant features, with statistical methods used to select optimal feature combinations. Notably, the fast Fourier transform (FFT) proves effective for acoustic-based leak localization, enhancing model accuracy. Lastly, a novel data-driven leak pinpointing method is introduced, leveraging machine learning regression techniques and a continuously updated database. The Decision Tree algorithm emerges as a robust choice for pinpointing leaks, offering high predictive accuracy across diverse leak scenarios. In new case studies for validating the proposed method, the selected model can predict the leakage point within 1 m with 96.7% accuracy, and the prediction reduces the potential leakage scope to within 0.3 m.