
Probabilistic leak localization in water distribution networks using a hybrid data-driven and model-based approach
- Author
- Ganjour Mazaev, Michael Weyns (UGent) , Filip Vancoillie, Guido Vaes, Femke Ongenae (UGent) and Sofie Van Hoecke (UGent)
- Organization
- Project
- Abstract
- In this paper, a hybrid leak localization approach in WDNs is proposed, combining both model-based and data-driven modeling. Pressure heads of leak scenarios are simulated using a hydraulic model, and then used to train a machine-learning based leak localization model. A key element of the methodology is that discrepancies between simulated and measured pressures are accounted for using a dynamically calculated bias correction, based on historical pressure measurements. Data of in -field leak experiments in operational water distribution networks were produced to evaluate our approach on realistic test data. The results show that the leak localization model is able to reduce the leak search region in parts of the network where leaks induce detectable drops in pressure. When this is not the case, the model still localizes the leak but is able to indicate a higher level of uncertainty with respect to its leak predictions.
- Keywords
- hybrid, hydraulic model, leak localization, machine learning, pressure, head, water distribution network, SYSTEMS
Downloads
-
Publisher version.pdf
- full text (Published version)
- |
- open access
- |
- |
- 892.05 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01GPAXAF3P6959SBB6AQEA3PM1
- MLA
- Mazaev, Ganjour, et al. “Probabilistic Leak Localization in Water Distribution Networks Using a Hybrid Data-Driven and Model-Based Approach.” WATER SUPPLY, vol. 23, no. 1, 2023, pp. 162–78, doi:10.2166/ws.2022.416.
- APA
- Mazaev, G., Weyns, M., Vancoillie, F., Vaes, G., Ongenae, F., & Van Hoecke, S. (2023). Probabilistic leak localization in water distribution networks using a hybrid data-driven and model-based approach. WATER SUPPLY, 23(1), 162–178. https://doi.org/10.2166/ws.2022.416
- Chicago author-date
- Mazaev, Ganjour, Michael Weyns, Filip Vancoillie, Guido Vaes, Femke Ongenae, and Sofie Van Hoecke. 2023. “Probabilistic Leak Localization in Water Distribution Networks Using a Hybrid Data-Driven and Model-Based Approach.” WATER SUPPLY 23 (1): 162–78. https://doi.org/10.2166/ws.2022.416.
- Chicago author-date (all authors)
- Mazaev, Ganjour, Michael Weyns, Filip Vancoillie, Guido Vaes, Femke Ongenae, and Sofie Van Hoecke. 2023. “Probabilistic Leak Localization in Water Distribution Networks Using a Hybrid Data-Driven and Model-Based Approach.” WATER SUPPLY 23 (1): 162–178. doi:10.2166/ws.2022.416.
- Vancouver
- 1.Mazaev G, Weyns M, Vancoillie F, Vaes G, Ongenae F, Van Hoecke S. Probabilistic leak localization in water distribution networks using a hybrid data-driven and model-based approach. WATER SUPPLY. 2023;23(1):162–78.
- IEEE
- [1]G. Mazaev, M. Weyns, F. Vancoillie, G. Vaes, F. Ongenae, and S. Van Hoecke, “Probabilistic leak localization in water distribution networks using a hybrid data-driven and model-based approach,” WATER SUPPLY, vol. 23, no. 1, pp. 162–178, 2023.
@article{01GPAXAF3P6959SBB6AQEA3PM1, abstract = {{In this paper, a hybrid leak localization approach in WDNs is proposed, combining both model-based and data-driven modeling. Pressure heads of leak scenarios are simulated using a hydraulic model, and then used to train a machine-learning based leak localization model. A key element of the methodology is that discrepancies between simulated and measured pressures are accounted for using a dynamically calculated bias correction, based on historical pressure measurements. Data of in -field leak experiments in operational water distribution networks were produced to evaluate our approach on realistic test data. The results show that the leak localization model is able to reduce the leak search region in parts of the network where leaks induce detectable drops in pressure. When this is not the case, the model still localizes the leak but is able to indicate a higher level of uncertainty with respect to its leak predictions.}}, author = {{Mazaev, Ganjour and Weyns, Michael and Vancoillie, Filip and Vaes, Guido and Ongenae, Femke and Van Hoecke, Sofie}}, issn = {{1606-9749}}, journal = {{WATER SUPPLY}}, keywords = {{hybrid,hydraulic model,leak localization,machine learning,pressure,head,water distribution network,SYSTEMS}}, language = {{eng}}, number = {{1}}, pages = {{162--178}}, title = {{Probabilistic leak localization in water distribution networks using a hybrid data-driven and model-based approach}}, url = {{http://doi.org/10.2166/ws.2022.416}}, volume = {{23}}, year = {{2023}}, }
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: