Abstract
This study examines the benefits and limitations of a convolutional neural network (CNN) burst detection model that accounts for spatially distributed information of pressure responses in a water distribution system (WDS), i.e., the differences between measured and predicted pressure data. To that end, a 2D CNN is applied to a smart WDS where all pressures and advanced metering infrastructure (AMI) end-user demands are measured. Here, a well-calibrated hydraulic model for a WDS in Austin, TX is analyzed with measured AMI demands to predict pressure surfaces that are provided to a CNN. Alternative image data structures are examined to evaluate their importance and two different data types, raw pressure data and pressure responses, are evaluated to investigate the benefits of linking CNN with hydraulic information. In addition, the effect of field measurement errors on detection results is examined for a range of error magnitudes. Finally, burst detection results of partial and full pressure meters are assessed to study the benefits of pressure supplemented AMI systems. Based on the numerical results, several conclusions are posed. First, network layout information should be incorporated into the image data structure. In addition, CNN should incorporate hydraulic information within AMI demands rather than using raw pressure data. Lastly, large measurement errors can mask the impact of small bursts and SCADA systems are insufficient to detect these failures. Thus, pressure supplemented AMI systems are recommended.
Similar content being viewed by others
Availability of Data and Materials
All of the data, models, and code that support the findings of this study are available from the corresponding author upon reasonable request.
References
American Water Works Association (AWWA) (2008) Water Audits and Loss Control Programs: M36, vol 36. American Water Works Association, Washington, DC
Blokker EJM (2010) Stochastic water demand modelling for a better understanding of hydraulics in water distribution networks. Ph.D. thesis, Dept of Water Manag Delft Univ of Technol
Duan L, Xie M, Wang J, Bai T (2018) Deep learning enabled intelligent fault diagnosis: Overview and applications. J Intell Fuzzy Syst 35(5):5771–5784
Fang Q, Zhang J, Xie C, Yang Y (2019) Detection of multiple leakage points in water distribution networks based on convolutional neural networks. Water Supply 19(8):2231–2239
Gupta A, Kulat KD (2018) A selective literature review on leak management techniques for water distribution system. Water Resour Manag 32:3247–3269
Hagos M, Jung D, Lansey KE (2016) Optimal meter placement for pipe burst detection in water distribution systems. J Hydroinf 18(4):741–756
Hu Z, Chen B, Chen W, Tan D, Shen D (2021) Review of model-based and data-driven approaches for leak detection and location in water distribution systems. Water Supply 21(7):3282–3306
Hu X, Han Y, Yu B, Geng Z, Fan J (2021b) Novel leakage detection and water loss management of urban water supply network using multiscale neural networks. J Clean Prod 278:123611
Huang Y, Zheng F, Kapelan Z, Savic D, Duan HF, Zhang Q (2020) Efficient leak localization in water distribution systems using multistage optimal valve operations and smart demand metering. Water Resour Res 56(10):e2020WR028285. https://doi.org/10.1029/2020WR028285
Hwang H, Lansey K (2017) Water distribution system classification using system characteristics and graph-theory metrics. J Water Resour Plan Manag 143(12):04017071
Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. Int Conf on Mach Learn 448–456. PMLR
Javadiha M, Blesa J, Soldevila A, Puig V (2019) Leak localization in water distribution networks using deep learning. Int Conf on Control Decis Inform Technol (CoDIT) 1426–1431. IEEE. https://doi.org/10.1109/CoDIT.2019.8820627
Jun S, Lansey KE (2023) Linear programming models for leak detection and localization in water distribution networks. J Water Resour Plan Manag 149(5):04023017. https://doi.org/10.1061/JWRMD5.WRENG-5720
Kim S, Jun S, Jung D (2022) Ensemble CNN model for effective pipe burst detection in water distribution systems. Water Resour Manag 36(13):5049–5061
Kumar SS, Abraham DM, Jahanshahi MR, Iseley T, Starr J (2018) Automated defect classification in sewer closed circuit television inspections using deep convolutional neural networks. Autom Constr 91:273–283
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444. https://doi.org/10.1038/nature14539
Lee CW, Yoo DG (2021) Development of leakage detection model and its application for water distribution networks using RNN-LSTM. Sustainability 13(16):9262
Mounce SR, Machell J (2006) Burst detection using hydraulic data from water distribution systems with artificial neural networks. Urban Water J 3(1):21–31
Romano M, Kapelan Z, Savić DA (2010) Real-time leak detection in water distribution systems. Water Distrib Syst Anal 2010 1074–1082
Romano M, Woodward K, Kapelan Z (2017) Statistical process control based system for approximate location of pipe bursts and leaks in water distribution systems. Procedia Eng 186:236–243
Rossman LA, Woo H, Tryby M, Shang F, Janke R, Haxton T (2020) EPANET 2.2 user’s manual, water infrastructure division. Center for Environmental Solutions and Emergency Response
Schmidhuber J (2015) Deep learning in neural networks: An overview. Neural Netw 61:85–117
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Teng S, Chen G, Gong P, Liu G, Cui F (2020) Structural damage detection using convolutional neural networks combining strain energy and dynamic response. Meccanica 55(4):945–959
Vrachimis SG, Eliades DG, Taormina R, Ostfeld A, Kapelan Z, Liu S, Kyriakou MS, Pavlou P, Qiu M, Polycarpou M (2020) Dataset of BattLeDIM: Battle of the leakage detection and isolation methods. Proc Int CCWI/WDSA Joint Conf Kingston, ON, Canada: Queen's Univ
Wang X, Guo G, Liu S, Wu Y, Xu X, Smith K (2020) Burst detection in district metering areas using deep learning method. J Water Resour Plan Manag 146(6):04020031
Ye G, Fenner RA (2014) Weighted least squares with expectation-maximization algorithm for burst detection in UK water distribution systems. J Water Resour Plan Manag 140(4):417–424
Zhou X, Tang Z, Xu W, Meng F, Chu X, Xin K, Fu G (2019) Deep learning identifies accurate burst locations in water distribution networks. Water Res 166:115058
Funding
This material is based in part upon the work supported by the National Science Foundation (NSF) under Grant No. 1762862. Any opinions, finding, and conclusions or recommendations expressed in this material are those of author(s) and do not necessarily reflect the views of the NSF.
Author information
Authors and Affiliations
Contributions
Data and code generations and their analysis were performed, and the first draft of the manuscript was written by Sanghoon Jun. Kevin E. Lansey guided the study and reviewed, edited, and approved the manuscript. Both authors edited and approved the final manuscript.
Corresponding author
Ethics declarations
Ethics Approval
Not applicable.
Consent to Participate and for Publication
Not applicable. Research did not involve human subjects.
Competing Interests
The authors have no conflicts of interest to declare.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jun, S., Lansey, K.E. Convolutional Neural Network for Burst Detection in Smart Water Distribution Systems. Water Resour Manage 37, 3729–3743 (2023). https://doi.org/10.1007/s11269-023-03524-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11269-023-03524-x