In this paper two models are presented based on Data-Driven Modeling (DDM) techniques (Artificial Neural Network and neuro-fuzzy systems) for more comprehensive and more accurate prediction of the pipe failure rate and an improved assessment of the reliability of pipes. Furthermore, a multivariate regression approach has been developed to enable comparison with the DDM-based methods. Unlike the existing simple regression models for prediction of pipe failure rates in which only few factors of diameter, age and length of pipes are considered, in this paper other parameters such as pressure and pipe depth, are also included. Furthermore, an investigation is carried out on most commonly used mechanical reliability relationships and the results of incorporation of the proposed pipe failure models in the reliability index are compared. The proposed models are applied to a real case study involving a large water distribution network in Iran and the results of model predictions are compared with measured pipe failure data. Compared with the results of neuro-fuzzy and multivariate regression models, the outcomes of the artificial neural network model are more realistic and accurate in the prediction of pipe failure rates and evaluation of mechanical reliability in water distribution networks.

This paper presents a new way of interpreting the results of the traditional demand-driven network analysis as an approximation to pressure-driven simulation so as to calculate the reliability of single-source networks. The approach is useful because most network modeling software packages use the demand-driven analysis approach and are incapable of simulating pressure-deficient conditions properly. The formulation draws from recent developments in pressure-driven simulation and can be used to calculate the reliability of an entire water distribution network or that of the individual demand nodes. The method herein is probabilistic in that the random nature of link failures is accounted for. Using a sample network, it is shown that the method has several advantages including simplicity and a very high computational efficiency.