Using Artificial Neural Network surrogate model to reduce the calculations of leak detection in water distribution networks

Document Type : Research Article

Authors

Department of Civil Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.

Abstract

The leak detection parameters in the inverse transient analysis (ITA) are obtained in an inverse approach by solving a nonlinear programming problem using metaheuristic algorithms such as genetic algorithms (GA). Beside its high capability in deriving the leak detection parameters, the ITA method is computationally complex and costly. Applying optimization techniques like GA can reduce the complexcity of the ITA method. This study aims to increase the computational efficiency by employing surrogate models in the optimization process of the ITA method. The surrogate model is in fact a simulated sample of the main model capable of approximately calculating the objective function in a fraction of a second. The way these models are integrated into the optimization model highly affects their success or failure. To this end, two algorithms incorporating population-based surrogate models, namely (Pre-selection Strategy) PS and (Best Strategy) BS, were presented. To evaluate and compare the results, a distribution network was used to identify the leak detection parameters. The results indicated an increase in the computational efficiency compared to the ITA method integrated with the GA. The PS algorithm demonstrated the highest performance by reducing the objective function and time complexity by 58% and 78%, respectively.

Keywords

Main Subjects

References

[1] R. Puust, Z. Kapelan, D. Savic, T.J.U.W.J. Koppel, A review of methods for leakage management in pipe networks, 7(1) (2010) 25-45.
[2] I. Barradas, L.E. Garza, R. Morales-Menendez, A. VargasMartínez, Leaks detection in a pipeline using artificial neural networks, in:  Iberoamerican Congress on Pattern Recognition, Springer, (2009), pp. 637-644.
[3] S. Sarkamaryan, A. Haghighi, A.J.J.o.W.S.R. Adib, Technology-Aqua, Leakage detection and calibration of pipe networks by the inverse transient analysis modified by Gaussian functions for leakage simulation, 67(4) (2018) 404-413.
[4] J.P. Vitkovsky, M.F. Lambert, A.R. Simpson, X.-J. Wang, An experimental verification of the inverse transient technique for leak detection, in:  6th Conference on Hydraulics in Civil Engineering: The State of Hydraulics; Proceedings, Institution of Engineers, Australia, (2001), pp. 373.
[5] Z.S. Kapelan, D.A. Savic, G.A. Walters, A hybrid inverse transient model for leakage detection and roughness calibration in pipe networks, Journal of Hydraulic Research, 41(5) (2003) 481-492.
[6] A. Haghighi, C. Covas, H. Ramos, Modified inverse transient analysis for leak detection of pressurized pipes, BHR group pressure surges, (2012).
[7] R.S. Pudar, J.A. Liggett, Leaks in pipe networks, Journal of Hydraulic Engineering, 118(7) (1992) 1031-1046.
[8] J.P. Vítkovský, A.R. Simpson, M.F. Lambert, Leak detection and calibration using transients and genetic algorithms, Journal of water resources planning and management, 126(4) (2000) 262-265.
[9] H. Shamloo, A. Haghighi, Optimum leak detection and calibration of pipe networks by inverse transient analysis, Journal of Hydraulic Research, 48(3) (2010) 371-376.
[10] A. Haghighi, H.M. Ramos, Detection of leakage freshwater and friction factor calibration in drinking networks using central force optimization, Water resources management, 26(8) (2012) 2347-2363.
[11] C.-C.J.W. Lin, A hybrid heuristic optimization approach for leak detection in pipe networks using ordinal optimization approach and the symbiotic organism search, 9(10) (2017) 812.
[12] S. Sarkamaryan, A. Haghighi, A. Adib, Leakage detection and calibration of pipe networks by the inverse transient analysis modified by Gaussian functions for leakage simulation, Journal of Water Supply: Research and Technology-Aqua, 67(4) (2018) 404-413.
[13] Y. Tenne, C.-K. Goh, Computational intelligence in expensive optimization problems, Springer Science & Business Media, (2010).
[14] L. Gräning, Y. Jin, B. Sendhoff, Individual-based management of meta-models for evolutionary optimization with application to three-dimensional blade optimization, in:  Evolutionary computation in dynamic and uncertain environments, Springer, (2007), pp. 225-250
[15] A.C. Caputo, P.M. Pelagagge, Using neural networks to monitor piping systems, Process Safety Progress, 22(2) (2003) 119-127.
[16] C. Sivapragasam, R. Maheswaran, V. Venkatesh, ANNbased model for aiding leak detection in water distribution networks, Asian Journal of Water, Environment and Pollution, 5(3) (2008) 111-114.
[17] M. Romano, Z. Kapelan, D. Savić, Real-time leak detection in water distribution systems, in:  Water Distribution Systems Analysis 2010, (2010), pp. 1074-1082.
[18] M. ATTARI, M.M. FAGHFOUR, New Method for Leakage Detection by Using Artificial Neural Networks, (2018).
[19] H. Hao, J. Zhang, A. Zhou, A Comparison Study of Surrogate Model Based Preselection in Evolutionary Optimization, in:  International Conference on Intelligent Computing, Springer, (2018), pp. 717-728.
[20] Y.J.S. Jin, E. Computation, Surrogate-assisted evolutionary computation: Recent advances and future challenges, 1(2) (2011) 61-70.
[21] M.H. Chaudhry, Applied hydraulic transients, Springer, (1979).
[22] A. Haghighi, H.J.P.I.C.E.W.M. Shamloo, Transient generation in pipe networks for leak detection, 164(6) (2011) 311-318.
Amirkabir Journal of Civil Engineering
Volume 52, Issue 10
January 2021
Pages 2635-2648

Files

Share

How to cite

Statistics