Forecasting breakage rate in water distribution networks using evolutionary polynomial regression Karimian, F.; Elsawah, H.; Zayed, T.; Moselhi, O.; Al Hawari, A.
The economic, social and environmental impact of water main failures impose great pressure on utility managers and municipalities to develop reliable rehabilitation/replacement plans. The annual number of breaks or breakage rate of each pipe segment is known as one of the most important criteria in condition assessment of these pipelines. A model is developed in this research to predict the annual number of breaks in water pipes. The developed model utilizes Evolutionary Polynomial Regression (EPR), which is intuitive data mining technique. The model is applied to a case study to test its effectiveness. The case considers the water distribution networks of in the cities of Doha in Qatar; Montréal, Moncton and Hamilton in Canada. The results indicated that the developed models successfully estimated the breakage rate for the city of Montréal and the number of breaks for the city of Doha with a maximum coefficient of determination of 88.51% and 96.27% respectively. This demonstrates the accuracy and robustness of the developed models in forecasting the number of breaks and breakage rate in water distribution networks.
Item Citations and Data
Attribution-NonCommercial-NoDerivs 2.5 Canada