Abstract
AbstractResearchers and engineers employ machine learning (ML) tools to detect pipe bursts and prevent significant non-revenue water losses in water distribution systems (WDS). Nonetheless, many approaches developed so far consider a fixed number of sensors, which requires the ML model redevelopment and collection of sufficient data with the new sensor configuration for training. To overcome these issues, this study presents a novel approach based on Long Short-Term Memory neural networks (NNs) that leverages transfer learning to manage a varying number of sensors and retain good detection performance with limited training data. The proposed detection model first learns to reproduce the normal behavior of the system on a dataset obtained in burst-free conditions. The training process involves predicting flow and pressure one-time step ahead using historical data and time-related features as inputs. During testing, a post-prediction step flags potential bursts based on the comparison between the observations and model predictions using a time-varied error threshold. When adding new sensors, we implement transfer learning by replicating the weights of existing channels and then fine-tune the augmented NN. We evaluate the robustness of the methodology on simulated fire hydrant bursts and real-bursts in 10 district metered areas (DMAs) of the UK. For real bursts, we perform a sensitivity analysis to understand the impact of data resolution and error threshold on burst detection performance. The results obtained demonstrate that this ML-based methodology can achieve Precision of up to 98.1% in real-life settings and can identify bursts, even in data scarce conditions.
Publisher
Springer Science and Business Media LLC
Subject
Water Science and Technology,Civil and Structural Engineering
Reference34 articles.
1. Adedeji K, Hamam Y, Abe B, Abu-Mahfouz A (2017) Towards achieving a reliable leakage detection and localization algorithm for application in water piping networks: An overview. IEEE Access 5:20272–20285. https://doi.org/10.1109/ACCESS.2017.2752802
2. Al-washali T, Sharma S, Kennedy M (2016) Methods of assessment of water losses in water supply systems: a review. Water Resour Manag 30:4985–5001. https://doi.org/10.1007/s11269-016-1503-7
3. Bakker M, Vreeburg JH, Rietveld LC, Van De Roer M (2012) Reducing customer minutes lost by anomaly detection?. In WDSA 2012: 14th Water Distribution Systems Analysis Conference, 24-27 September 2012 in Adelaide, South Australia. Barton, ACT: Engineers Australia, pp 913–927. https://search.informit.org/doi/10.3316/informit.946749511368491
4. Bentivoglio R, Isufi E, Jonkman SN, Taormina R (2022) Deep learning methods for flood mapping: a review of existing applications and future research directions. Hydrol Earth Syst Sci 26(16):4345–4378. https://doi.org/10.5194/hess-26-4345-2022
5. Caputo AC, Pelagagge PM (2003) Using neural networks to monitor piping systems. Process Saf Prog 22(2):119–127. https://doi.org/10.1002/prs.680220208
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献