Application of genetic programming to modeling pipe failures in water distribution systems

The water loss from a water distribution system is a serious problem for many cities, which incurs enormous economic and social loss. However, the economic and human resource costs to exactly locate the leakage are extraordinarily high. Thus, reliable and robust pipe failure models are demanded to assess a pipe's propensity to fail. Beijing City was selected as the case study area and the pipe failure data for 19 years (1987-2005) were analyzed. Three different kinds of methods were applied to build pipe failure models. First, a statistical model was built, which discovered that the ages of leakage pipes followed the Weibull distribution. Then, two other models were developed using genetic programming (GP) with different data pre-processing strategies. The three models were compared thereafter and the best model was applied to assess the criticality of all the pipe segments of the entire water supply network in Beijing City based on GIS data.

[1]  D. Savić,et al.  Advances in data-driven analyses and modelling using EPR-MOGA. , 2009 .

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

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

[4]  Lisa A Jeffrey.  Predicting urban water distribution maintenance strategies : a case study of New Haven, Connecticut , 1985 .

[5]  Dragan Savic,et al.  Whole Life Costing for Water Distribution Network Management , 2003 .

[6]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

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

[8]  Luigi Berardi,et al.  Development of pipe deterioration models for water distribution systems using EPR , 2008 .

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

[10]  D. Savić,et al.  A symbolic data-driven technique based on evolutionary polynomial regression , 2006 .

[11]  Daniele B. Laucelli,et al.  Asset deterioration analysis using multi-utility data and multi-objective data mining , 2009 .

[12]  Sveinung Sægrov,et al.  Statistical approach for describing failures and lifetimes of water mains , 1998 .

[13]  Balvant Rajani,et al.  Using limited data to assess future needs , 1999 .

[14]  Jean-Pierre Villeneuve,et al.  Modeling Water Pipe Breaks—Three Case Studies , 2003 .

[15]  O. Giustolisi.  Using genetic programming to determine Chèzy resistance coefficient in corrugated channels , 2004 .

[16]  Magnus Moglia,et al.  A physical probabilistic model to predict failure rates in buried PVC pipelines , 2007, Reliab. Eng. Syst. Saf..

[17]  Seth D. Guikema,et al.  Statistical models for the analysis of water distribution system pipe break data , 2009, Reliab. Eng. Syst. Saf..

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

[19]  Balvant Rajani,et al.  Comprehensive review of structural deterioration of water mains: physically based models , 2001 .

[20]  G. Pelletier,et al.  Modeling the evolution of the structural state of water pipe networks with brief recorded pipe break histories: Methodology and application , 2000 .

[21]  Riccardo Poli,et al.  Foundations of Genetic Programming , 1999, Springer Berlin Heidelberg.

[22]  Vladan Babovic,et al.  A Data Mining Approach to Modelling of Water Supply Assets , 2002 .

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