Multiobjective Wrapper Sampling Design for Leak Detection of Pipe Networks Based on Machine Learning and Transient Methods
Publication: Journal of Water Resources Planning and Management
Volume 149, Issue 2
Abstract
This study introduces a novel sampling design (SD) method for hybrid Machine Learning/Transient-Based (ML/TB) leak detection of pipe networks. The proposed technique exploits the hydraulic responses of the network in the frequency domain and the concept of Filter and Wrapper feature selection as a machine learning approach. It also utilizes multiobjective optimization to handle the trade-off between leak detection error and number of sampling nodes. To apply this method, a transient hydraulic simulation model of the network is developed in the time domain. Then, considering a wide range of leak scenarios, the hydraulic responses of the network are calculated at candidate measurement sites. The responses are then transferred into the frequency domain using the Fast Fourier Transform (FFT) and stored as the train and test datasets. To reduce the dimensions of the initial feature vector, a threshold is applied to the responses to filter the very high frequencies. Finally, a classifier based on a Linear Discriminant Algorithm (LDA) coupled to a binary-coded Non-dominated Sorting Genetic Algorithm (NSGA-II) is applied to preprocessed datasets. Four sampling design methods are adopted from the literature and modified in the frequency domain for more investigations and comparisons. Solving two example pipe networks showed that the proposed method outperforms the existing approaches with respect to higher accuracy leak detection with fewer sampling sites.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
The datasets generated and analyzed during the current study are available from the corresponding author upon reasonable request.
Acknowledgments
The authors would like to thank the corresponding Associate Editor and anonymous reviewers for their constructive comments and suggestions.
References
Ayati, A. H., A. Haghighi, and H. R. Ghafouri. 2022a. “Machine learning—Assisted model for leak detection in water distribution networks using hydraulic transient flows.” J. Water Resour. Plann. Manage. 148 (2): 04021104. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001508.
Ayati, A. H., A. Haghighi, and H. R. Ghafouri. 2022b. “Machine learning approach to transient-based leak detection of pressurized pipelines: Classification vs regression.” J. Civ. Struct. Health Monit. 12 (3): 611–628. https://doi.org/10.1007/s13349-022-00568-2.
Ayati, A. H., A. Haghighi, and P. Lee. 2019. “Statistical review of major standpoints in hydraulic transient-based leak detection.” J. Hydraul. Struct. 5 (1): 1–26. https://doi.org/10.22055/jhs.2019.27926.1095.
Beck, S. B. M., J. Foong, and W. J. Staszewski. 2006. “Wavelet and cepstrum analyses of leaks in pipe networks.” In Progress in Industrial Mathematics at ECMI 2004. Berlin: Springer.
Berry, J. W., W. E. Hart, C. A. Phillips, and J.-P. Watson. 2008. “A facility location approach to sensor placement optimization.” In Proc., Water Distribution Systems Analysis Symp. 2006, 1–4. Reston, VA: ASCE. https://doi.org/10.1061/40941(247)111.
Bohorquez, J., B. Alexander, R. Simpson Angus, and F. Lambert Martin. 2020. “Leak detection and topology identification in pipelines using fluid transients and artificial neural networks.” J. Water Resour. Plann. Manage. 146 (6): 04020040. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001187.
Brunone, B. 1999. “Transient test-based technique for leak detection in outfall pipes.” J. Water Resour. Plann. Manage. 125 (5): 302–306. https://doi.org/10.1061/(ASCE)0733-9496(1999)125:5(302).
Bush, C. A., and J. G. Uber. 1998. “Sampling design methods for water distribution model calibration.” J. Water Resour. Plann. Manage. 124 (6): 334–344. https://doi.org/10.1061/(ASCE)0733-9496(1998)124:6(334).
Cai, J., J. Luo, S. Wang, and S. Yang. 2018. “Feature selection in machine learning: A new perspective.” Neurocomputing 300 (3): 70–79. https://doi.org/10.1016/j.neucom.2017.11.077.
Candelieri, A., D. Soldi, D. Conti, and F. Archetti. 2014. “Analytical leakages localization in water distribution networks through spectral clustering and support vector machines. The icewater approach.” Procedia Eng. 89 (11): 1080–1088. https://doi.org/10.1016/j.proeng.2014.11.228.
Caputo, A. C., and P. M. Pelagagge. 2003. “Using neural networks to monitor piping systems.” Process Saf. Prog. 22 (2): 119–127. https://doi.org/10.1002/prs.680220208.
Casillas, M. V., V. Puig, L. E. Garza-Castañón, and A. Rosich. 2013. “Optimal sensor placement for leak location in water distribution networks using genetic algorithms.” Sensors (Basel) 13 (11): 14984–15005. https://doi.org/10.3390/s131114984.
Chaudhry, M. H. 2016. Applied hydraulic transients. New York: Springer.
Covas, D., and H. Ramos. 2001. “Hydraulic transients used for leakage detection in water distribution systems.” In Proc., 4th Int. Conf. Water Pipeline System, 227–241. Cranfield, UK: BHR Group.
Covas, D., and H. Ramos. 2010. “Case studies of leak detection and location in water pipe systems by inverse transient analysis.” J. Water Resour. Plann. Manage. 136 (2): 248–257. https://doi.org/10.1061/(ASCE)0733-9496(2010)136:2(248).
Das, S. 2001. “Filters, wrappers and a boosting-based hybrid for feature selection.” In Proc., 18th Int. Conf. on Machine Learning (ICML-2001), 74–81. San Francisco: Morgan Kaufmann.
Deb, K., A. Pratap, S. Agarwal, and T. Meyarivan. 2002. “A fast and elitist multiobjective genetic algorithm: NSGA-II.” IEEE Trans. Evol. Comput. 6 (2): 182–197. https://doi.org/10.1109/4235.996017.
Duan, H. F., and P. J. Lee. 2016. “Transient–based frequency domain method for dead-end side branch detection in reservoir pipeline-valve systems.” J. Hydraul. Eng. 142 (2): 04015042. https://doi.org/10.1061/(ASCE)HY.1943-7900.0001070.
Duan, H.-F. 2017. “Transient frequency response based leak detection in water supply pipeline systems with branched and looped junctions.” J. Hydroinf. 19 (1): 17–30. https://doi.org/10.2166/hydro.2016.008.
Duan, H.-F., P. J. Lee, M. S. Ghidaoui, and Y.-K. Tung. 2010. “Essential system response information for transient-based leak detection methods.” J. Hydraul. Res. 48 (5): 650–657. https://doi.org/10.1080/00221686.2010.507014.
Duan, H.-F., P. J. Lee, M. S. Ghidaoui, and Y.-K. Tung. 2011. “Leak detection in complex series pipelines by using the system frequency response method.” J. Hydraul. Res. 49 (2): 213–221. https://doi.org/10.1080/00221686.2011.553486.
Duan, H. F. J. 2018. “Accuracy and sensitivity evaluation of TFR method for leak detection in multiple-pipeline.” Water Supply Syst. 32 (Feb): 2147–2164. https://doi.org/10.1007/s11269-018-1923-7.
Fan, X., and X. Yu. 2021. “An innovative machine learning based framework for water distribution network leakage detection and localization.” Struct. Health Monit. 21 (4): 14759217211040269. https://doi.org/10.1177/14759217211040269.
Farley, B., S. R. Mounce, and J. B. Boxall. 2010. “Field testing of an optimal sensor placement methodology for event detection in an urban water distribution network.” Urban Water J. 7 (6): 345–356. https://doi.org/10.1080/1573062X.2010.526230.
Farley, B., S. R. Mounce, and J. B. Boxall. 2013. “Development and field validation of a burst localization methodology.” J. Water Resour. Plann. Manage. 139 (6): 604–613. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000290.
Ferrante, M., B. Brunone, S. Meniconi, B. W. Karney, and C. Massari. 2014. “Leak size, detectability and test conditions in pressurized pipe systems.” Water Resour. Manage. 28 (13): 4583–4598. https://doi.org/10.1007/s11269-014-0752-6.
Forconi, E., Z. Kapelan, M. Ferrante, H. Mahmoud, and C. Capponi. 2017. “Risk-based sensor placement methods for burst/leak detection in water distribution systems.” Water Supply 17 (6): 1663–1672. https://doi.org/10.2166/ws.2017.069.
Gertler, J. 1998. Fault detection and diagnosis in engineering systems. 1st ed. London: CRC Press.
Ghanbari, N. 2019. A review of feature selection methods with the applications in pattern recognition in the last decade. Singapore: Fundamental Research in Electrical Engineering.
Gupta, G. 2017. “Monitoring water distribution network using machine learning. (Independent thesis advanced level (degree of Master (Two Years)) Student thesis.)” Accessed January 26, 2018. https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-221832.
Haghighi, A., and H. M. Ramos. 2012. “Detection of leakage freshwater and friction factor calibration in drinking networks using central force optimization.” Water Resour. Manage. 26 (8): 2347–2363. https://doi.org/10.1007/s11269-012-0020-6.
Haghighi, A., and H. Shamloo. 2011. “Transient generation in pipe networks for leak detection.” Proc. Inst. Civ. Eng. Water Manage. 164 (6): 311–318. https://doi.org/10.1680/wama.2011.164.6.311.
Hagos, M., D. Jung, and K. E. Lansey. 2016. “Optimal meter placement for pipe burst detection in water distribution systems.” J. Hydroinf. 18 (4): 741–756. https://doi.org/10.2166/hydro.2016.170.
Jović, A., K. Brkić, and N. Bogunović. 2015. “A review of feature selection methods with applications.” In Proc., 2015 38th Int. Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO). Piscataway, NJ: IEEE. https://doi.org/10.1109/MIPRO.2015.7160458.
Jung, D., and J. H. Kim. 2018. “Using mechanical reliability in multiobjective optimal meter placement for pipe burst.” Detection 144 (7): 04018031. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000953.
Kapelan Zoran, S., A. Savic Dragan, and A. Walters Godfrey. 2003. “Multiobjective sampling design for water distribution model calibration.” J. Water Resour. Plann. Manage. 129 (6): 466–479. https://doi.org/10.1061/(ASCE)0733-9496(2003)129:6(466.
Kapelan Zoran, S., A. Savic Dragan, and A. Walters Godfrey. 2005. “Optimal sampling design methodologies for water distribution model calibration.” J. Hydraul. Eng. 131 (3): 190–200. https://doi.org/10.1061/(ASCE)0733-9429(2005)131:3(190).
Kaufman, L., and P. J. Rousseeuw. 1990. “Partitioning around medoids (Program PAM).” In Finding groups in data, 68–125. Hoboken, NJ: Wiley.
Khilqa, S., M. Elkholy, M. Al-Tofan, M. Caicedo Juan, and M. H. Chaudhry. 2019. “Damping in transient pressurized flows.” J. Hydraul. Eng. 145 (10): 04019034. https://doi.org/10.1061/(ASCE)HY.1943-7900.0001624.
Langley, P. 1994. “Selection of relevant features in machine learning.” In Proc., AAAI Fall Symp. on Relevance, 245–271. Palo Alto, California: Association for the Advancement of Artificial Intelligence.
Lee, P. J., H.-F. Duan, J. Tuck, and M. Ghidaoui. 2014. “Numerical and experimental study on the effect of signal bandwidth on pipe assessment using fluid transients.” J. Hydraul. Eng. 141 (2): 04014074. https://doi.org/10.1061/(ASCE)HY.1943-7900.0000961.
Lee, P. J., M. F. Lambert, A. R. Simpson, J. P. Vítkovský, and J. Liggett. 2006. “Experimental verification of the frequency response method for pipeline leak detection.” J. Hydraul. Res. 44 (5): 693–707. https://doi.org/10.1080/00221686.2006.9521718.
Lee, P. J., J. P. Vítkovský, M. F. Lambert, A. R. Simpson, and J. A. Liggett. 2005a. “Frequency domain analysis for detecting pipeline leaks.” J. Hydraul. Eng. 131 (7): 596–604. https://doi.org/10.1061/(ASCE)0733-9429(2005)131:7(596).
Lee, P. J., J. P. Vítkovský, M. F. Lambert, A. R. Simpson, and J. A. Liggett. 2005b. “Leak location using the pattern of the frequency response diagram in pipelines: A numerical study.” J. Sound Vib. 284 (3): 1051–1073. https://doi.org/10.1016/j.jsv.2004.07.023.
Leu, S.-S., and Q.-N. Bui. 2016. “Leak prediction model for water distribution networks created using a Bayesian network learning approach.” Water Resour. Manage. 30 (8): 2719–2733. https://doi.org/10.1007/s11269-016-1316-8.
Levinas, D., G. Perelman, and A. Ostfeld. 2021. “Water leak localization using high-resolution pressure sensors.” Water 13 (5): 50–59. https://doi.org/10.3390/w13050591.
Liggett, A., and L. C. Chen. 1994. “Inverse transient analysis in pipe networks.” J. Hydraul. Eng. 120 (8): 934–955. https://doi.org/10.1061/(ASCE)0733-9429(1994)120:8(934).
Mashford, J., D. De Silva, S. Burn, and D. Marney. 2012. “Leak detection in simulated water pipe networks using SVM.” Appl. Artif. Intell. 26 (5): 429–444. https://doi.org/10.1080/08839514.2012.670974.
Meniconi, S., B. Brunone, M. Ferrante, C. Capponi, C. A. Carrettini, C. Chiesa, and E. A. Lanfranchi. 2014. “Anomaly pre-localization in distribution–transmission mains by pump trip: Preliminary field tests in the Milan pipe system.” J. Hydroinf. 17 (3): 377–389. https://doi.org/10.2166/hydro.2014.038.
Mohammed, E. G., E. B. Zeleke, and S. L. Abebe. 2021. “Water leakage detection and localization using hydraulic modeling and classification.” J. Hydroinf. 23 (4): 782–794. https://doi.org/10.2166/hydro.2021.164.
Ostfeld, A., et al. 2008. “The battle of the water sensor networks (BWSN): A design challenge for engineers and algorithms.” J. Water Resour. Plann. Manage. 134 (6): 556–568. https://doi.org/10.1061/(ASCE)0733-9496(2008)134:6(556)).
Pan, B., A. Keramat, C. Capponi, S. Meniconi, B. Brunone, and H. F. Duan. 2022. “Transient energy analysis in water-filled viscoelastic pipelines.” J. Hydraul. Eng. 148 (1): 04021051. https://doi.org/10.1061/(ASCE)HY.1943-7900.0001959.
Pérez, R., V. Puig, J. Pascual, A. Peralta, E. Landeros, and L. Jordanas. 2009. “Pressure sensor distribution for leak detection in Barcelona water distribution network.” Water Supply 9 (6): 715–721. https://doi.org/10.2166/ws.2009.372.
Plath, M., E. Mathias, and W. Knut. 2014. “Energy efficiency and energy saving in the German water industry.” Water Pract. Technol. 9 (2): 256–263. https://doi.org/10.2166/wpt.2014.029.
Poulakis, Z., D. Valougeorgis, and C. Papadimitriou. 2003. “Leakage detection in water pipe networks using a Bayesian probabilistic framework.” Probab. Eng. Mech. 18 (4): 315–327. https://doi.org/10.1016/S0266-8920(03)00045-6.
Ranginkaman, M. H., A. H. Ayati, A. E. Bakhshipour, and A. Haghighi. 2019a. “Transient measurement site design in pipe networks using the decision table method (DTM).” J. Hydraul. Struct. 5 (2): 32–48. https://doi.org/10.22055/jhs.2019.29402.1107.
Ranginkaman, M. H., A. Haghighi, and P. J. Lee. 2019b. “Frequency domain modelling of pipe transient flow with the virtual valves method to reduce linearization errors.” Mech. Syst. Sig. Process. 131 (4): 486–504. https://doi.org/10.1016/j.ymssp.2019.05.065.
Ranginkaman, M. H., A. Haghighi, and H. M. Vali Samani. 2016. “Inverse frequency response analysis for pipelines leak detection using the particle swarm optimization.” IUST 6 (1): 1–12.
Sabzkouhi, A. M., and A. Haghighi. 2018. “Uncertainty analysis of transient flow in water distribution networks.” Water Resour. Manage. 32 (12): 3853–3870. https://doi.org/10.1007/s11269-018-2023-4.
Sankary, N., and A. Ostfeld. 2017. “Scaled multiobjective optimization of an intensive early warning system for water distribution system security.” J. Hydraul. Eng. 143 (9): 04017025. https://doi.org/10.1061/(ASCE)HY.1943-7900.0001317.
Sarkamaryan, S., A. Haghighi, S. M. Ashrafi, and H. M. V. Samani. 2020. “Surrogate-assisted inverse transient analysis (SAITA) for leakage detection in pressurized piping systems.” Iran. J. Sci. Technol. Trans. Civ. Eng. 45 (4): 2707–2718.https://doi.org/10.1007/s40996-020-00516-4.
Shamloo, H., and A. Haghighi. 2009. “Leak detection in pipelines by inverse backward transient analysis.” J. Hydraul. Res. 47 (3): 311–318. https://doi.org/10.1080/00221686.2009.9522002.
Simone, A., O. Giustolisi, and D. B. Laucelli. 2016. “A proposal of optimal sampling design using a modularity strategy.” Water Resour. Res. 52 (8): 6171–6185. https://doi.org/10.1002/2016WR018944.
Soldevila, A., R. M. Fernandez-Canti, J. Blesa, S. Tornil-Sin, and V. Puig. 2017. “Leak localization in water distribution networks using Bayesian classifiers.” J. Process Control 55 (4): 1–9. https://doi.org/10.1016/j.jprocont.2017.03.015.
Tao, T., H. Huang, F. Li, and K. Xin. 2014. “Burst detection using an artificial immune network in water-distribution.” Systems 140 (10): 04014027. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000405.
Vitkovsky, J. P., F. Lambert Martin, R. Simpson Angus, and A. Liggett James. 2007. “Experimental observation and analysis of inverse transients for pipeline leak detection.” J. Water Resour. Plann. Manage. 133 (6): 519–530. https://doi.org/10.1061/(ASCE)0733-9496(2007)133:6(519.
Vitkovsky, J. P., J. A. Liggett, A. R. Simpson, and M. F. Lambert. 2003. “Optimal measurement site locations for inverse transient analysis in pipe networks.” J. Water Resour. Plann. Manage. 129 (6): 480–492. https://doi.org/10.1061/(ASCE)0733-9496(2003)129:6(480.
Vitkovsky, P., R. Simpson, and F. Lambert. 2000. “Leak detection and calibration using transients and genetic algorithms.” J. Water Resour. Plann. Manage. 126 (4): 262–265. https://doi.org/10.1061/(ASCE)0733-9496(2000)126:4(262).
Walski, T. M. 1983. “Technique for calibrating network models.” J. Water Resour. Plann. Manage. 109 (4): 360–372. https://doi.org/10.1061/(ASCE)0733-9496(1983)109:4(360).
Wang, X., J. Lin, and S. Ghidaoui Mohamed. 2020. “Usage and effect of multiple transient tests for pipeline leak detection.” J. Water Resour. Plann. Manage. 146 (11): 06020011. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001284.
Wang, X., J. Lin, A. Keramat, M. S. Ghidaoui, S. Meniconi, and B. Brunone. 2019. “Matched-field processing for leak localization in a viscoelastic pipe: An experimental study.” Mech. Syst. Sig. Process. 124 (Feb): 459–478. https://doi.org/10.1016/j.ymssp.2019.02.004.
Waqar, M., M. Louati, X. Wang, and S. Ghidaoui Mohamed. 2021. “Model-free matched field processing for condition assessment of pressurized pipes.” J. Water Resour. Plann. Manage. 147 (10): 04021066. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001447.
Xing, L., T. Raviv, and L. Sela. 2022. “Sensor placement for robust burst identification in water systems: Balancing modeling accuracy, parsimony, and uncertainties.” Adv. Eng. Inf. 51 (Mar): 101484. https://doi.org/10.1016/j.aei.2021.101484.
Xu, X., and B. Karney. 2017. “An overview of transient fault detection techniques.” In Modeling and monitoring of pipelines and networks: Advanced tools for automatic monitoring and supervision of pipelines, 13–37. Berlin: Springer.
Zecchin Aaron, C., R. Simpson Angus, F. Lambert Martin, B. White Langford, and P. Vítkovský John. 2009. “Transient modeling of arbitrary pipe networks by a Laplace-Domain admittance matrix.” J. Eng. Mech. 135 (6): 538–547. https://doi.org/10.1061/(ASCE)0733-9399(2009)135:6(538.
Zeng, W., J. Gong, R. Simpson Angus, S. Cazzolato Benjamin, C. Zecchin Aaron, and F. Lambert Martin. 2020. “Paired-IRF method for detecting leaks in pipe networks.” J. Water Resour. Plann. Manage. 146 (5): 04020021. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001193.
Zhang, Q., Y. Wu Zheng, M. Zhao, J. Qi, Y. Huang, and H. Zhao. 2016. “Leakage zone identification in large-scale water distribution systems using multiclass support vector machines.” J. Water Resour. Plann. Manage. 142 (11): 04016042. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000661.
Zhao, Z., F. Morstatter, S. Sharma, S. Alelyani, A. Anand, and H. Liu. 2010. Advancing feature selection research, ASU feature selection repository, 1–28. NSF-0812551. Tempe, AZ: Arizona State Univ.
Information & Authors
Information
Published In
Journal of Water Resources Planning and Management
Volume 149 • Issue 2 • February 2023
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Oct 29, 2021
Accepted: Sep 14, 2022
Published online: Nov 16, 2022
Published in print: Feb 1, 2023
Discussion open until: Apr 16, 2023
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Computer programming
- Computing in civil engineering
- Continuum mechanics
- Detection methods
- Dynamics (solid mechanics)
- Engineering fundamentals
- Engineering mechanics
- Environmental engineering
- Filters
- Filtration
- Hybrid methods
- Hydraulic engineering
- Hydraulic networks
- Hydraulic structures
- Infrastructure
- Methodology (by type)
- Pipe leakage
- Pipe networks
- Pipeline management
- Pipeline systems
- Pipes
- Solid mechanics
- Transient response
- Water and water resources
- Water treatment
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.