An unsupervised approach to leak detection and location in water distribution networks

• Autorzy: Quiñones-Grueiro M. , Verde C. , Prieto-Moreno A. , Llanes-Santiago O.

Identyfikatory

DOI

10.2478/amcs-2018-0020

• Języki publikacji: EN

Abstrakty

EN

The water loss detection and location problem has received great attention in recent years. In particular, data-driven methods have shown very promising results mainly because they can deal with uncertain data and the variability of models better than model-based methods. The main contribution of this work is an unsupervised approach to leak detection and location in water distribution networks. This approach is based on a zone division of the network, and it only requires data from a normal operation scenario of the pipe network. The proposition combines a periodic transformation and a data vector extension together with principal component analysis of leak detection. A reconstruction-based contribution index is used for determining the leak zone location. The Hanoi distribution network is employed as the case study for illustrating the feasibility of the proposal. Single leaks are emulated with varying outflow magnitudes at all nodes that represent less than 2.5% of the total demand of the network and between 3% and 25% of the node’s demand. All leaks can be detected within the time interval of a day, and the average classification rate obtained is 85.28% by using only data from three pressure sensors.

Słowa kluczowe

EN

water distribution network; leak location; unsupervised methods; principal component analysis; demand model

PL

sieć wodociągowa; lokalizacja wycieku; analiza składników głównych; model popytu

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2018
• Tom: Vol. 28, no. 2
• Strony: 283--295
• Opis fizyczny: Bibliogr. 35 poz., rys., tab., wykr.

Twórcy

autor

Quiñones-Grueiro M.

• Department of Automation and Computing, Havana University of Technologies José Antonio Echeverría (CUJAE), 114, e/ Ciclovía y Rotonda, Marianao, 19390, La Habana, Cuba

autor

Verde C.

• Institute of Engineering, National Autonomous University of Mexico (UNAM), Coyoacán, 04510 México DF, Mexico

autor

Prieto-Moreno A.

• Department of Automation and Computing, Havana University of Technologies José Antonio Echeverría (CUJAE), 114, e/ Ciclovía y Rotonda, Marianao, 19390, La Habana, Cuba

autor

Llanes-Santiago O.

• Department of Automation and Computing, Havana University of Technologies José Antonio Echeverría (CUJAE), 114, e/ Ciclovía y Rotonda, Marianao, 19390, La Habana, Cuba

Bibliografia

• [1] Aksela, K., Aksela,M. and Vahala, R. (2009). Leakage detection in a real distribution network using a SOM, Urban Water Journal 6(4): 279–289.
• [2] Alcala, C.F. and Qin, S.J. (2009). Reconstruction-based contribution for process monitoring, Automatica 45(7): 1593–1600.
• [3] Beghi, A., Brignoli, R., Cecchinato, L., Menegazzo, G., Rampazzo, M. and Simmini, F. (2016). Data-driven fault detection and diagnosis for HVAC water chillers, Control Engineering Practice 53: 79–91.
• [4] Chiang, L.H., Rusell, E. and Braatz, R.D. (2001). Fault Detection and Diagnosis in Industrial Systems, Springer, London.
• [5] Colombo, A.F. and Kamey, B.W. (2002). Energy and costs of leaky pipes: Toward comprehensive picture, Journal of Water Resource Planning and Management 128(6): 441–450.
• [6] Fujiwara, O. and Khang, D.B. (1990). A two-phase decomposition method for optimal design of looped water distribution networks, Water Resources Research 26(4): 539–549.
• [7] Houghtalen, R.J., Akan, A.O. and Hwang, N.H.C. (2010). Fundamentals of Hydraulic Engineering Systems, 4th Edn., Prentice Hall, Englewood Cliffs, NJ.
• [8] Jung, D. and Lansey, K. (2015). Water distribution system burst detection using a nonlinear Kalman filter, Journal of Water Resources Planning and Management 141(5): 1–13.
• [9] Ku, W., Storer, R.H. and Georgakis, C. (1995). Disturbance detection and isolation by dynamic principal component analysis, Chemometrics and Intelligent Laboratory Systems 30: 179–196.
• [10] Łangowski, R. and Brdys, M.A. (2017). An interval estimator for chlorine monitoring in drinking water distribution systems under uncertain system dynamics, inputs and chlorine concentration measurement errors, International Journal of Applied Mathematics and Computer Science 27(2): 309–322, DOI: 10.1515/amcs-2017-0022.
• [11] Laucelli, D., Romano, M., Savic, D. and Giustolisi, O. (2016). Detecting anomalies in water distribution networks using EPR modelling paradigm, Journal of Hydroinformatics 18(3): 409–427.
• [12] Kościelny, J.M., Syfert, M., Rostek, K. and Sztyber, A. (2017). Fault isolability with different forms of the faults–symptoms relation, International Journal of Applied Mathematics and Computer Science 26(4): 815–826, DOI: 10.1515/amcs-2016-0058.
• [13] Moczulski, W., Wycz, R., Ciupke, K., Przystałka, P., Tomasik, P. and Wachla, D. (2016). A methodology of leakage detection and location in water distribution networks—The case study, Conference on Control and Fault Tolerant Systems SysTol, Barcelona, Spain, pp. 331–336.
• [14] Montgomery, D.C. and Runger, G.C. (2014). Applied Statistics and Probability for Engineers, 6th Edn., Wiley, Hoboken, NJ.
• [15] Mounce, S.R., Mounce, R.B., Jackson, T., Austin, J. and Boxall, J.B. (2014). Pattern matching and associative artificial neural networks for water distribution system time series data analysis, Journal of Hydroinformatics 16(3): 617–632.
• [16] Nowicki, A., Grochowski, M. and Duzinkiewicz, K. (2012). Data-driven models for fault detection using kernel PCA: A water distribution system case study, International Journal of Applied Mathematics and Computer Science 22(4): 939–949, DOI: 10.2478/v10006-012-0070-1.
• [17] Olsson, G. (2006). Instrumentation, control and automation in the water industry—State-of-the-art and new challenges, Water Science and Technology 53(4–5): 1–16.
• [18] Palau, C.V., Arregui, F.J. and Carlos, M. (2012). Burst detection in water networks using principal component analysis, Journal of Water Resources Planning and Management 138(1): 47–54.
• [19] Papoulis, A. (1991). Probability, Random Variables, and Stochastic Processes, 3rd Edn., McGraw-Hill, New York, NY.
• [20] Quiñones-Grueiro, M., Verde, C. and Llanes-Santiago, O. (2017). Features of demand patterns for leak detection in water distribution networks, in C. Verde and L. Torres (Eds.), Modeling and Monitoring of Pipelines and Networks, Springer, Cham, Chapter 9, pp. 171–189.
• [21] Quiñones-Grueiro, M., Verde, C. and Prieto-Moreno, A. (2016). Leaks’ detection in water distribution networks with demand patterns, 3rd Conference on Control and Fault Tolerant Systems SysTol, Barcelona, Spain, pp. 313–318.
• [22] Rato, T.J. and Reis, M.S. (2013). Defining the structure of DPCA models and its impact on process monitoring and prediction activities, Chemometrics and Intelligent Laboratory Systems 125: 74–86.
• [23] Romano, M., Kapelan, Z. and Savić, D.A. (2010). Real-time leak detection in water distribution systems, Water Distribution Systems Analysis Conference, ASCE, Tucson, AZ, USA, pp. 1074–1082.
• [24] Romano, M., Kapelan, Z. and Savic, D.A. (2013). Geostatistical techniques for approximate location of pipe burst events in water distribution systems, Journal of Hydroinformatics 15(3): 634–652.
• [25] Rossman, L.A. (2000). Epanet 2 User’s Manual, Technical report, United States Envionmental Protection Agency, http://www.epa.gov/nrmrl/wswrd/dw/epanet.html.
• [26] Sanz, G., Pérez, R., Kapelan, Z., Savic, D. and Asce, A.M. (2015). Leak detection and localization through demand components calibration, Journal of Water Resources Planning and Management 142(2): 1–13.
• [27] Sedki, A. and Ouazar, D. (2012). Hybrid particle swarm optimization and differential evolution for optimal design of water distribution systems, Advanced Engineering Informatics 26(3): 582–591.
• [28] Soldevila, A., Blesa, J., Tornil-Sin, S., Duviella, E., Fernandez-Canti, R.M. and Puig, V. (2016). Leak localization in water distribution networks using a mixed model-based/data-driven approach, Control Engineering Practice 55: 162–173.
• [29] Soldevila, A., Fernandez-Canti, R.M., Blesa, J., Tornil-Sin, S. and Puig, V. (2017). Leak localization in water distribution networks using Bayesian classifiers, Journal of Process Control 55: 1–9.
• [30] Wachla, D., Przystalka, P.and Moczulski, W. (2015). A method of leakage location in water distribution networks using artificial-neuro fuzzy system, IFAC-PapersOnLine 48(21): 1216–1223.
• [31] Wang, J., Member, S., Chen, T., Member, S. and Huang, B. (2006). Cyclo-period estimation for discrete-time cyclo-stationary signals, IEEE Transactions on Signal Processing 54(1): 83–94.
• [32] Wu, Y., Liu, S., Wu, X., Liu, Y. and Guan, Y. (2016). Burst detection in district metering areas using a data driven clustering algorithm, Water Research 100: 28–37.
• [33] Yue, H.H. and Qin, S.J. (2001). Reconstruction-based fault identification using a combined index, Industrial & Engineering Chemistry Research 40(20): 4403–4414.
• [34] Zhang, Q., Wu, Z.Y., Zhao, M., Qi, J., Huang, Y. and Zhao, H. (2016). Leakage zone identification in large-scale water distribution systems using multiclass support vector machines, Journal of Water Resources Planning and Management 142(11): 1–15.
• [35] Zhou, S.L., McMahon, T.A., Walton, A. and Lewis, J. (2002). Forecasting operational demand for an urban water supply zone, Journal of Hydrology 259(1–4): 189–202.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2018).