Machine Learning for Water Leak Detection and Localization in the WaterPrime Project
Data
2023
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
Lodz University of Technology Press
Abstrakt
We present an integrated approach for water leak detection and localization
developed for the WaterPrime project. Proposed method is based
on telemetric monitoring of a District Metered Areas (DMA), using first an
application of anomaly detection on sensors’ data and then building a ‘digital
twin’ of a DMA state using a combination of hydraulic simulator and
machine learning algorithms. This approach leads to reduction of time of
leak location estimation from the order of weeks/months to days, and provides
a significant reduction in quantity of water lost, as was preliminary
verified in two waterworks associated with the project.
Opis
Słowa kluczowe
leak detection, leak localization, anomaly detection in time series, machine learning of a digital twin, detekcja wycieków, lokalizacja wycieków, wykrywanie anomalii w szeregach czasowych, uczenie maszynowe cyfrowego bliźniaka
Cytowanie
Głomb P., Romaszewski M., Cholewa M., Koral W., Madej A., Skrabski M., Kołodziej K., Machine Learning for Water Leak Detection and Localization in the WaterPrime Project. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 193-194, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.30.