A Probabilistic Digital Twin for Leak Localization in Water Distribution Networks Using Generative Deep Learning
Sensors · 05.07.2023 · 23 (13) · 6179
DOI: 10.3390/s23136179 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 05.07.2023. Verfasst von Nikolaj T Mücke und 4 weiteren Autor:innen. Beteiligte Einrichtung: Centrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The Netherlands. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Dutch Research Council, the Dutch National Science Foundation NWO.
Abstract (Originalsprache)
Localizing leakages in large water distribution systems is an important and ever-present problem. Due to the complexity originating from water pipeline networks, too few sensors, and noisy measurements, this is a highly challenging problem to solve. In this work, we present a methodology based on generative deep learning and Bayesian inference for leak localization with uncertainty quantification. A generative model, utilizing deep neural networks, serves as a probabilistic surrogate model that replaces the full equations, while at the same time also incorporating the uncertainty inherent in such models. By embedding this surrogate model into a Bayesian inference scheme, leaks are located by combining sensor observations with a model output approximating the true posterior distribution for possible leak locations. We show that our methodology enables producing fast, accurate, and trustworthy results. It showed a convincing performance on three problems with increasing complexity. For a simple test case, the Hanoi network, the average topological distance (ATD) between the predicted and true leak location ranged from 0.3 to 3 with a varying number of sensors and level of measurement noise. For two more complex test cases, the ATD ranged from 0.75 to 4 and from 1.5 to 10, respectively. Furthermore, accuracies upwards of 83%, 72%, and 42% were achieved for the three test cases, respectively. The computation times ranged from 0.1 to 13 s, depending on the size of the neural network employed. This work serves as an example of a digital twin for a sophisticated application of advanced mathematical and deep learning techniques in the area of leak detection.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Centrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The Netherlands.
- Mathematical Institute, Utrecht University, 3584 CS Utrecht, The Netherlands.
- Department of Management Studies, Indian Institute of Science, Bangalore 560012, India.
- Swammerdam Institute of Life Sciences (SILS), University of Amsterdam, 1098 XH Amsterdam, The Netherlands.
- Bernoulli Institute, Rijksuniversiteit Groningen, 9747 AG Groningen, The Netherlands.
ORCID-Profile: Nikolaj T Mücke, Prerna Pandey, Shashi Jain, Sander M Bohté, Cornelis W Oosterlee
Förderung
- Dutch Research Council
- the Dutch National Science Foundation NWO
Zitieren
APA
Mücke, N. T., Pandey, P., Jain, S., Bohté, S. M., & Oosterlee, C. W. (2023). A Probabilistic Digital Twin for Leak Localization in Water Distribution Networks Using Generative Deep Learning. Sensors, 23(13), 6179. https://doi.org/10.3390/s23136179
Vancouver
Mücke NT, Pandey P, Jain S, Bohté SM, Oosterlee CW. A Probabilistic Digital Twin for Leak Localization in Water Distribution Networks Using Generative Deep Learning. Sensors. 2023;23(13):6179. doi:10.3390/s23136179
BibTeX
@article{Mcke2023,
author = {Mücke, Nikolaj T and Pandey, Prerna and Jain, Shashi and Bohté, Sander M and Oosterlee, Cornelis W},
title = {A Probabilistic Digital Twin for Leak Localization in Water Distribution Networks Using Generative Deep Learning},
journal = {Sensors},
year = {2023},
volume = {23},
number = {13},
pages = {6179},
doi = {10.3390/s23136179}
}
EUVIMED