Pipeline failure prediction in water distribution networks using weather conditions as explanatory factors

Abstract

Abstract This paper examines the impact of weather conditions on pipe failure in water distribution networks using artificial neural network (ANN) and evolutionary polynomial regression (EPR). A number of weather-related factors over 4 consecutive days are the input of the binary ANN model while the output is the occurrence or not of at least a failure during the following 2 days. The model is able to correctly distinguish the majority (87%) of the days with failure(s). The EPR is employed to predict the annual number of failures. Initially, the network is divided into six clusters based on pipe diameter and age. The last year of the monitoring period is used for testing while the remaining years since the beginning are retained for model development. An EPR model is developed for each cluster based on the relevant training data. The results indicate a strong relationship between the annual number of failures and frequency and intensity of low temperatures. The outputs from the EPR models are used to calculate the failures of the homogenous groups within each cluster proportionally to their length.