New Approach for Prediction of Water Distribution Network Pipes Failure Based on a Intelligent Hybrid Model (Case Study: Gorgan Water Distribution Network)

Document Type : Complete scientific research article


1 Water engineering department-Agriculture Faculty-Gorgan-Iran Gorgan Agriculture sciences and Natural Resources

2 Campus of Agriculture and Natural Resources, University of Tehran

3 Civil Engineering Department- Engineering and Technical Faculty-Mazandaran University


Background and Objective: Urban water distribution networks consider as one of the essential infrastructural facilities and equipment in urban areas. The pipes are one of the primary and essential components of a water distribution network break during operation due to various factors. So, developing models for pipes failure rate prediction can be one of the most crucial tools for managers and stakeholders to the optimal operation of the water distribution network. In the last decade, various studies have performed to predict the failure rate of water distribution pipes using statistical and soft models - each of which has strengths and weaknesses. This study aims to present a new approach based on the development of a hybrid prediction model, considering the capabilities of soft and statistical models, to more accurately predict the water distribution network pipes failure rate compared to statistical and soft models used in previous research.
Material and Method: In order to achieve the study goals, 4-year (2015-2018) time duration statistics of Gorgan water distribution network characteristics including diameter, length, age, depth of installation, and the number of pipe failures used to predict future pipes failure rates. To modeling the pipe failure rate of the investigated network, five different models, including three statistical models (linear regression, generalized linear regression, support vector regression) and two soft models (feed-forward neural network, and radial basis function neural network) has studied. Optimal parameters of the models were selected based on appropriate statistical error indicators, including correlation coefficient (R), Mean Square Error (MSE), and Correlation Mean square error Ratio (CMR) for the training and testing data. In order to select the best model from different models to predict the failure rate of network pipes, the values of R and MSE indicators of the above models were calculated in the validation stage and compared with each other. Finally, to predict pipes failure rate more accurately, a new approach is developed based on the hybrid prediction model in which the predicted values of pipe failure rates by statistical and soft computing models considered as independent variables of the best model inputs and the observed values of failure rates as dependent variables of the best model outputs.
Results: Comparing the values of R and MSE indicators of each statistical and soft computing model used in this study in the validation phase show that these models cannot predict the pipes' failure rate with reasonable accuracy. Feed forward neural network model with the highest R = 0.69 and the lowest MSE = 0.062 values has the best estimates. Using the new approach developed based on hybrid soft and statistical models, the R index is equal to 0.96, and the MSE index is equal to 0.046.
Conclusion: A significant increase in the R index (39%) and decrease in the MSE index (25%) through using the proposed hybrid approach compared to the feed-forward neural network model demonstrates that using the new approach provides perfect accuracy prediction of the pipes failure rate of the water distribution network.


1.Aydogdu, M., and Firat. M. 2015. Estimation of failure rate in water distribution network using fuzzy clustering and LS-SVM methods. Water resources management 29: 5. 1575-1590.
2.Asnaashari, A., McBean, E. A., Gharabaghi, B., and Tutt, D. 2013. Forecasting watermain failure using artificial neural network modelling. Canadian Water Resour. J. 38: 1. 24-33.
3.Berardi, L., Giustolisi, O., Kapelan, Z., and Savic, D.A. 2008. Development of pipe deterioration models for water distribution systems using EPR. J. Hydroinf. 10: 2. 113-126.
4.Farmani, R., Kakoudakis, K., Behzadian Moghadam, K., and Butler, D. 2017. Pipe failure prediction in water distribution systems considering static and dynamic factors. Procedia Engineering, 186: 117-126.
5.Fares, H., and Zayed, T. 2010. Hierarchical fuzzy expert system for risk of failure of water mains. J. Pipeline Syst. Engin. Prac. 1: 1. 53-62.
6.Faris Hamdala, K., and Sagar, G. 2016. Statistical Analysis of Pipe Breaks in Water Distribution Systems in Ethiopia, the Case of Hawassa.
7.Ghasemnejad, S., and Nodoshan, M.S. 2014. Prediction of water distribution network pipes Vulnerability by developing statistical models. Iranian Congress of Water and Wastewater Engineering. (In Persian)
8.Ho, C.I., Lin, M.D., and Lo, S.L. 2010. Use of a GIS-based hybrid artificial neural network to prioritize the order of pipe replacement in a water distribution network. Environmental monitoring and assessment, 166: 1-4. 177-189.
9.Islam, M.S., Sadiq, R., Rodriguez, M.J., Francisque, A., Najjaran, H., and Hoorfar, M. 2011. Leakage detection and location in water distribution systems using a fuzzy-based methodology. Urban Water J. 8: 6. 351-365.
10.Jafar, R., Shahrour, I., and Juran, I. 2010. Application of Artificial Neural Networks (ANN) to model the failure of urban water mains. Mathematical and Computer Modelling, 51: 9-1. 1170-1180.
11.Kerwin, S., de Soto, B.G., and Adey, B.T. 2019. Performance comparison for pipe failure prediction using artificial neural networks. In 6th International Symposium on Life-Cycle Civil Engineering, IALCCE 2018 (pp. 1337-1342). CRC Press/Balkema.
12.Kakoudakis, K., Behzadian, K., Farmani, R., and Butler, D. 2017. Pipeline failure prediction in water distribution networks using evolutionary polynomial regression combined with K-means clustering. Urban Water J.14: 7. 737-742.
13.Kleiner, Y., and Rajani, B. 2002. Forecasting variations and trends in water-main breaks. J. Infrastruc. Syst.8: 4. 122-131.
14.Kapelan, Z.S., Savic, D.A., and Walters, G.A. 2003. A hybrid inverse transient model for leakage detection and roughness calibration in pipe networks. J. Hydr. Res. 41: 5. 481-492.
15.Motiee, H., and Ghasemnejad, S. 2019. Prediction of pipe failure rate in Tehran water distribution networks by applying regression models. Water Supply,19: 3. 695-702.
16.Mounce, S.R., Day, A.J., Wood, A.S., Khan, A., Widdop, P.D., and Machell, J. 2002. A neural network approach to burst detection. Water science and technology, 45: 4-5. 237-246.
17.Pandey, P., Dongre, S., and Gupta, R .2020. Probabilistic and fuzzy approaches for uncertainty consideration in water distribution networks–a review. Water supply. 20: 1. 13-27.
18.Robles-Velasco, Alicia, Pablo Cortés, Jesús Muñuzuri, and Luis Onieva. "Prediction of pipe failures in water supply networks using logistic regression and support vector classification." Reliability Engineering & System Safety. 196 (2020): 106754.
19.Rohan Dipakkumar Kania, S.S. 2017. Risk assessment of water distribution network using fuzzy based system. Inter. J. Adv. Res. Engin. Sci. Manage.
20.Rajani, B., and Kleiner, Y. 2001. Comprehensive review of structural deterioration of water mains: physically based models. Urban water, 3: 3. 151-164.
21.Rogers, P.D., and Grigg, N.S. 2009. Failure assessment modeling to prioritize water pipe renewal: two case studies. J. Infrastruc. Syst. 15: 3. 162-171.
22.Sadiq, R., Kleiner, Y., and Rajani, B. 2007. Water quality failures in distribution networks-risk analysis using fuzzy logic and evidential reasoning. Risk Analysis: An Inter. J. 27: 5. 1381-1394.
23.Shamir, U., and Howard, C.D. 1979. An analytic approach to scheduling pipe replacement. J. Amer. Water Work Assoc. 71: 5. 248-258.
24.Shirzad, A., Tabesh, M., and Farmani, R. 2014. A comparison between performance of support vector regression and artificial neural network in prediction of pipe burst rate in water distribution networks. KSCE J. Civil Engin. 18: 4. 941-948.
25.Soltani, J., and Tabari Rezapour, M. 2012. Determination of effective parameters in pipe failure rate in water distribution system using the combination of artificial neural networks and genetic algorithm. J. Water Waste 83: 2-18.
26.Sattar, A.M., Gharabaghi, B., and McBean, E.A. 2016. Prediction of timing of watermain failure using gene expression models. Water resources management, 30: 5. 1635-1651.
27.Soltanjalili, M., Bozorg-Haddad, O., and Mariño, M.A. 2011. Effect of breakage level one in design of water distribution networks. Water resources management, 25: 1. 311-337.
28.Sacluti, F.R. 1999. Modelling water distribution pipe failures using artificial neural networks.
29.Tabari, M.M.R., and Malekpour Shahraki, M.M. 2018.Reservoir Water Level Prediction Using Supervised Intelligent Committee Machine Method, Case Study: Karaj Amirkabir Dam. Iran-Water Resources Research, 14: 5. 15-30 (In Persian)
30.Tavakoli, R., Najafi, M., and Sharifara, A. 2019. Artificial Neural Networks and Adaptive Neuro-fuzzy Models for Prediction of Remaining Useful Life. arXiv preprint arXiv:1909.02115.
31.Tu, M.Y., Tsai, F.T.C., and Yeh, W.W.G. 2005. Optimization of water distribution and water quality by hybrid genetic algorithm. J. Water Resour. Plan. Manage. 131: 6. 431-440.
32.Wang, Y., Zayed, T., and Moselhi, O. 2009. Prediction models for annual break rates of water mains. J. Perform. Construc. Facilit. 23: 1. 47-54.
33.Xu, Q., Chen, Q., Ma, J., and Blanckaert, K. 2014. Optimal pipe replacement strategy based on break rate prediction through genetic programming for water distribution network. J. Hydro-Environ. Res. 7: 2. 134-140.
34.Xu, Q., Chen, Q., Li, W., andMa, J. 2011. Pipe break predictionbased on evolutionary data-driven methods with brief recorded data. Reliability Engineering & System Safety, 96: 8. 942-948.