Forecasting failure rate of water pipes

Abstract

This paper presents the results of failure rate prediction by means of support vector machines (SVM) – a non-parametric regression method. A hyperplane is used to divide the whole area in such a way that objects of different affiliation are separated from one another. The number of support vector determines the complexity of the relations between dependent and independent variables. The calculations were performed using Statistical 12.0. Operational data (provided by the Water Utility) for one selected zone of the water supply system for the period 2008–2014 were used for forecasting. The whole data set (in which data on distribution pipes were distinguished from those on house connections) for the years 2008–2014 was randomly divided into two subsets: a training subset – 75% (5 years) and a testing subset – 25% (2 years). Dependent variables ( λ r for the distribution pipes and λ p for the house connections) were forecasted using independent variables (the total length – L r and L p and number of failures – N r and N p of the distribution pipes and the house connections, respectively). Four kinds of kernel functions: linear, polynomial, sigmoidal and radial basis functions were applied. The SVM model based on the linear kernel function was found to be optimal for predicting the failure rate of each kind of water conduit. This model9s maximum relative error of predicting failure rates λ r and λ p during the testing stage amounted to about 4% and 14%, respectively. The average experimental failure rates in the whole analysed period amounted to 0.18, 0.44, 0.17 and 0.24 fail./(km·year) for the distribution pipes, the house connections and the distribution pipes made of respectively PVC and cast iron.