Forecasting Water Main Failure Using Artificial Neural Network and Generalized Linear Models

The city of Kingston, Ontario, is currently experiencing elevated costs to repair its aging buried water main assets. The application of a predictive water main break model allows for the estimation of pipe condition and likelihood of failure. The objective of this paper is to develop a generalized linear model (GLM) and artificial neural network (ANN) model to forecast pipe breaks in the Kingston water distribution network. Data supplied by Utilities Kingston was used to develop the predictive water main break models, incorporating multiple variables, data history, calibration, and data prioritization. The goal of these models is to provide a practical means to assist in the management and development of Kingston's pipe rehabilitation program and to enable Utilities Kingston to reduce water main repair costs and to improve water quality at the customer's tap. Models with acceptable precision will produce a reliable decision tool for future planning and budgeting.