Journal of Performance of Constructed Facilities, vol. 20, issue 2 (2006) pp. 126-135
One of the greatest challenges facing municipal engineers is the condition rating of buried infrastructure assets, particularly water mains. This is because water mains are typically underground, operated under pressure, and usually inaccessible. Condition rating is a mandatory process to establish and employ management strategies for any asset. To assess the condition of water mains, current research considers physical, environmental, and operational factors and their effect on different types of mains (i.e., cast iron, ductile iron, and asbestos). A condition rating model is developed to assess and set up rehabilitation priority for water mains using the artificial neural network (ANN) approach. Data are collected from different municipalities to train the developed model. The ANN input factors incorporate pipe type, size, age, breakage rate, Hazen-Williams factor, excavation depth, soil type, and top road surface; however, the output is pipe condition. The trained ANN shows robust performance (learning rate=0.005. R-2=0.931, correlation coefficient r=0.9653). Results show that the breakage rate has the highest relative contribution factor among the others. The developed model is relevant to researchers and practitioners (municipal engineers, consultants, and contractors) in order to prioritize pipe inspection and rehabilitation planning for existing water mains.
Mendeley saves you time finding and organizing research
Choose a citation style from the tabs below