Comparison of four models to rank failure likelihood of individual pipes

The use of statistical methods to discern patterns of historical breakage rates and use them to predict water main breaks has been widely documented. Particularly challenging is the prediction of breaks in individual pipes, due to the natural variations that exist in all the factors that affect their deterioration and subsequent failure. This paper describes alternative models developed into operational tools that can assist network owners and planners to identify individual mains for renewal in their water distribution networks. Four models were developed and compared: a heuristic model, a naive Bayesian classification model, a model based on logistic regression and finally a probabilistic model based on the non-homogeneous Poisson process (NHPP). These models rank individual water mains in terms of their anticipated breakage frequency, while considering both static (e.g. pipe material, diameter, vintage, surrounding soil, etc.) and dynamic (e.g. climate, operations, cathodic protection, etc.) effects influencing pipe deterioration rates.

[1]  I. C. Goulter,et al.  Spatial and temporal groupings of water main pipe breakage in Winnipeg , 1988 .

[2]  I. C. Goulter,et al.  An analysis of pipe breakage in urban water distribution networks , 1985 .

[3]  Balvant Rajani,et al.  Exploration of the relationship between water main breaks and temperature covariates , 2012 .

[4]  Balvant Rajani,et al.  Quantifying Effectiveness of Cathodic Protection in Water Mains: Theory , 2004 .

[5]  J. I. Ansell,et al.  Practical Methods for Reliability Data Analysis , 1994 .

[6]  Graeme C. Dandy,et al.  Optimal Scheduling of Water Pipe Replacement Using Genetic Algorithms , 2001 .

[7]  J. Villeneuve,et al.  Optimal replacement of water pipes , 2003 .

[8]  Diane Lambert,et al.  Zero-inflacted Poisson regression, with an application to defects in manufacturing , 1992 .

[9]  I. Goulter,et al.  Predicting Water-Main Breakage Rates , 1993 .

[10]  David H. Marks,et al.  A new methodology for modelling break failure patterns in deteriorating water distribution systems: Theory , 1987 .

[11]  Colin Christian,et al.  Bayesian-based pipe failure model , 2004 .

[12]  Zoran Kapelan,et al.  A ZERO-INFLATED BAYESIAN MODEL FOR THE PREDICTION OF WATER PIPE BURSTS , 2009 .

[13]  Jon Røstum,et al.  Statistical modelling of pipe failures in water networks , 2000 .

[14]  Thomas M. Walski,et al.  Economic analysis of water main breaks , 1982 .

[15]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[16]  Robert M. Clark,et al.  Water Distribution Systems: A Spatial and Cost Evaluation , 1982 .

[17]  Balvant Rajani,et al.  Comprehensive review of structural deterioration of water mains: statistical models , 2001 .

[18]  Yves Le Gat,et al.  Using maintenance records to forecast failures in water networks , 2000 .

[19]  Uri Shamir,et al.  An Analytic Approach to Scheduling Pipe Replacement , 1979 .