Bayesian Belief Networks for predicting drinking water distribution system pipe breaks

• Published in: Reliability engineering & system safety 2014-10, Vol.130, p.1-11
• Main Authors: Francis, Royce A., Guikema, Seth D., Henneman, Lucas
• Format: Article
• Language: English
• Subjects: Applied sciences; Asset management; Bayesian analysis; Bayesian Belief Networks; Belief networks; Breaking; Buildings. Public works; Distribution. Storage; Drinking water; Drinking water distribution systems; Exact sciences and technology; Expert systems; Firm modelling; Graphical models; Mathematical models; Operational research and scientific management; Operational research. Management science; Pipe; Reliability theory. Replacement problems; Water quality; Water supply. Pipings. Water treatment
• ISSN: 0951-8320; 1879-0836
• DOI: 10.1016/j.ress.2014.04.024

In this paper, we use Bayesian Belief Networks (BBNs) to construct a knowledge model for pipe breaks in a water zone. To the authors’ knowledge, this is the first attempt to model drinking water distribution system pipe breaks using BBNs. Development of expert systems such as BBNs for analyzing drinking water distribution system data is not only important for pipe break prediction, but is also a first step in preventing water loss and water quality deterioration through the application of machine learning techniques to facilitate data-based distribution system monitoring and asset management. Due to the difficulties in collecting, preparing, and managing drinking water distribution system data, most pipe break models can be classified as “statistical–physical” or “hypothesis-generating.” We develop the BBN with the hope of contributing to the “hypothesis-generating” class of models, while demonstrating the possibility that BBNs might also be used as “statistical–physical” models. Our model is learned from pipe breaks and covariate data from a mid-Atlantic United States (U.S.) drinking water distribution system network. BBN models are learned using a constraint-based method, a score-based method, and a hybrid method. Model evaluation is based on log-likelihood scoring. Sensitivity analysis using mutual information criterion is also reported. While our results indicate general agreement with prior results reported in pipe break modeling studies, they also suggest that it may be difficult to select among model alternatives. This model uncertainty may mean that more research is needed for understanding whether additional pipe break risk factors beyond age, break history, pipe material, and pipe diameter might be important for asset management planning. •We show Bayesian Networks for predictive and diagnostic management of water distribution systems.•Our model may enable system operators and managers to prioritize system surveillance.•We indicate key opportunities for future research in development of BBNs for infrastructure models.•We suggest a potential area of research includes the application of copula Bayesian Networks.