Estimation of the Short-Term Probability of Failure in Water Mains
Publication: Journal of Water Resources Planning and Management
Volume 143, Issue 2
Abstract
In this paper, the nonhomogeneous Poisson process (NHPP), hierarchical beta process (HBP), and a new-developed Bayesian simple model (BSM) are used for short-term failure prediction with several water utility failure data sets. The prediction curve was used to investigate the relative ranking of the pipes from the three models. The curve was demonstrated to be more suitable for practical situations compared to the traditional receiver operating characteristic (ROC) curve. The expected number of failures and the effect of incorporating covariates by dividing the pipe assets into smaller pressure cohorts were also examined. Based on the data sets used, the observations from the prediction curves show that the performance of the three models are very similar in terms of pipe ranking. However, the BSM is more advantageous because of its relative simplicity. The covariate, the number of known past failures, plays a very important role when considering the relative ranking of the pipes in the network. The NHPP and HBP are recommended if the total number of failures in the network is required. Subdividing one of the data sets (Data Set A) into a smaller pressure cohort showed improvement only for the prediction by the BSM. Unlike the NHPP, time is not specifically included in the HBP and BSM. Therefore, the HBP and BSM are not suitable for long-term predictions and cannot include time-dependent covariates.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
This publication is an outcome of the Smart Water Fund funded by South East Water, City West Water, Yarra Valley Water, and Melbourne Water. The project is also affiliated with the Advanced Condition Assessment and Pipeline Failure Prediction (ACAPFP). The authors would also like to thank the reviewers for their comments during the revision process of the paper.
References
Andreou, S. A., Marks, D. H., and Clark, R. M. (1987a). “A new methodology for modelling break failure patterns in deteriorating water distribution systems: Applications.” Adv. Water Resour., 10(1), 11–20.
Andreou, S. A., Marks, D. H., and Clark, R. M. (1987b). “A new methodology for modelling break failure patterns in deteriorating water distribution systems: Theory.” Adv. Water Resour., 10(1), 2–10.
BITRE (Bureau of Infrastructure, Transport and Regional Economics). (2014). “Yearbook 2014: Australian infrastructure statistical report.” Canberra, ACT, Australia.
Bubtiena, A. M., Elshafie, A. H., and Jafaar, O. (2011). “Application of artificial neural networks in modelling water networks.” IEEE 7th Int. Colloquium on Signal Processing and Its Applications (CSPA), 2011, IEEE, Piscataway, NJ, 50–57.
Cox, D. R. (1972). “Regression models and life tables.” J. R. Stat. Soc. Series B (Methodological), 34(2), 187–220.
Dandy, G., and Engelhardt, M. (2006). “Multi-objective trade-offs between cost and reliability in the replacement of water mains.” J. Water Resour. Plann. Manage., 79–88.
Davis, P., Burn, S., Moglia, M., and Gould, S. (2007). “A physical probabilistic model to predict failure rates in buried PVC pipelines.” Reliab. Eng. Syst. Saf., 92(9), 1258–1266.
Davis, P., Moglia, M., Burn, S., and Farlie, M. (2004). “Estimating failure probability from condition assessment of critical cast iron water mains.” Proc. 6th National Australasian Society for Trenchless Technology Conf., ASTT, Perth, WA, Australia.
Dridi, L., Mailhot, A., Parizeau, M., and Villeneuve, J. (2009). “Multiobjective approach for pipe replacement based on Bayesian inference of break model parameters.” J. Water Resour. Plann. Manage., 344–354.
Economou, T., Kapelan, Z., and Bailey, T. (2009). “A zero-inflated Bayesian model for the prediction of water pipe bursts.” Water Distribution Systems Analysis 2008, ASCE, Reston, VA, 1–11.
Fawcett, T. (2006). “An introduction to ROC analysis.” Pattern Recognit. Lett., 27(8), 861–874.
Gelman, A., Carlin, J., Stern, H., and Rubin, D. (2000). Bayesian data analysis, CRC Press, London.
Harvey, R., McBean, E., and Gharabaghi, B. (2014). “Predicting the timing of water main failure using artificial neural networks.” J. Water Resour. Plann. Manage., 425–434.
Jafar, R., Shahrour, I., and Juran, I. (2010). “Application of artificial neural networks (ANN) to model the failure of urban water mains.” Math. Comput. Modell., 51(9–10), 1170–1180.
Ji, J., Zhang, C., Kodikara, J., and Yang, S. Q. (2015). “Prediction of stress concentration factor of corrosion pits on buried pipes by least squares support vector machine.” Eng. Fail. Anal., 55, 131–138.
Kimutai, E., Betrie, G., Brander, R., Sadiq, R., and Tesfamariam, S. (2015). “Comparison of statistical models for predicting pipe failures: Illustrative example with the city of Calgary water main failure.” J. Pipeline Syst. Eng. Pract., .
Kleiner, Y., and Rajani, B. (2002). “Forecasting variations and trends in water-main breaks.” J. Infrastruct. Syst., 122–131.
Kleiner, Y., and Rajani, B. (2012). “Comparison of four models to rank failure likelihood of individual pipes.” J. Hydroinf., 14(3), 659–681.
Kunkel, G., Laven, K., and Mergelas, B. (2008). “Does your city have high-risk pipes?” J. Am. Water Works Assoc., 100(4), 70–74.
Kutylowska, M. (2015). “Modelling of failure rate of water-pipe networks.” Period. Polytech. Civ. Eng., 59(1), 37–43.
Lawless, J. F. (1987). “Regression methods for Poisson process data.” J. Am. Stat. Assoc., 82(399), 808–815.
Li, F., Ma, L., Sun, Y., and Mathew, J. (2015). “Optimized group replacement scheduling for water pipeline network.” J. Water Resour. Plann. Manage., .
Li, Z., Zhang, B., Wang, Y., Chen, F., Taib, R., Whiffin, V., and Wang, Y. (2014). “Water pipe condition assessment: A hierarchical beta process approach for sparse incident data.” Mach. Learn., 95(1), 11–26.
Lunn, D. J., Thomas, A., Best, N., and Spiegelhalter, D. (2000). “WinBUGS—A Bayesian modelling framework: Concepts, structure, and extensibility.” Stat. Comput., 10(4), 325–337.
Martins, A., Leitão, J. P., and Aamda, C. (2013). “Comparative study of three stochastic models for prediction of pipe failures in water supply systems.” J. Infrastruct. Syst., 442–450.
Moglia, M., Burn, S., and Meddings, S. (2006). “Decision support system for water pipeline renewal prioritisation.” ITcon, 11, 237–256.
Moglia, M., Davis, P., and Burn, S. (2008). “Strong exploration of a cast iron pipe failure model.” Reliab. Eng. Syst. Saf., 93(6), 885–896.
Moore, G. (2010). “Corrosion challenges—Urban water industry.”, Australasian Corrosion Association, Blackburn, VIC, Australia.
Nafi, A., and Kleiner, Y. (2010). “Scheduling renewal of water pipes while considering adjacency of infrastructure works and economies of scale.” J. Water Resour. Plann. Manage., 519–530.
NWC (National Water Commission). (2014). “National performance report 2012–13: Urban water utilities.” Canberra, ACT, Australia.
Park, S. (2011). “Estimating the timing of the economical replacement of water mains based on the predicted pipe break times using the proportional hazards models.” Water Resour. Manage., 25(10), 2509–2524.
Park, S., Jun, H., Agbenowosi, N., Kim, B. J., and Lim, K. (2011). “The proportional hazards modeling of water main failure data incorporating the time-dependent effects of covariates.” Water Resour. Manage., 25(1), 1–19.
Pelletier, G., Mailhot, A., and Villeneuve, J. 2003. “Modeling water pipe breaks—Three case studies.” J. Water Resour. Plann. Manage., 115–123.
Rajani, B., and Kleiner, Y. (2001). “Comprehensive review of structural deterioration of water mains: Physically based models.” Urban Water, 3(3), 151–164.
Rajani, B., and Kleiner, Y. (2008). “Prioritising individual water mains for renewal.” World Environmental and Water Resources Congress, ASCE, Reston, VA, 1–10.
Rajani, B., Kleiner, Y., and Sink, J.-E. (2012). “Exploration of the relationship between water main breaks and temperature covariates.” Urban Water J., 9(2), 67–84.
Rathnayaka, S., Keller, R., Kodikara, J., and Chik, L. (2016a). “Numerical simulation of pressure transients in water supply networks as applicable to critical water pipe asset management.” J. Water Resour. Plann. Manage., .
Rathnayaka, S., Shannon, B., Rajeev, P., and Kodikara, J. (2016b). “Monitoring of pressure transients in water supply networks.” Water Resour. Manage., 30(2), 471–485.
Røstum, J. (2000). “Statistical modeling of pipe failures in water networks.” Ph.D. thesis, Norwegian, Univ. of Science and Technology, Trondheim, Norway.
Shamir, U., and Howard, C. D. (1978). “An analytic approach to scheduling pipe replacement.” J. Am. Water Works Assoc., 71(5), 248–258.
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. Civ. Eng., 18(4), 941–948.
Thibaux, R., and Jordan, M. I. (2007). “Hierarchical beta processes and the Indian buffet process.” JMLR: Workshop and Conf. Proc., Vol. 2, 564–571.
Walski, T. M., and Pelliccia, A. (1982). “Economic analysis of water main breaks.” J. Am. Water Works Assoc., 74(3), 140–147.
Wang, Y., Zayed, T., and Moselhi, O. (2009). “Prediction models for annual break rates of water mains.” J. Perform. Constr. Facil., 47–54.
Information & Authors
Information
Published In
Journal of Water Resources Planning and Management
Volume 143 • Issue 2 • February 2017
Copyright
©2016 American Society of Civil Engineers.
History
Received: Mar 17, 2016
Accepted: Aug 16, 2016
Published online: Oct 17, 2016
Published in print: Feb 1, 2017
Discussion open until: Mar 17, 2017
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.