Full Description

Although failures in water distribution systems are inevitable, compromising the levels ofservice to the consumer during failures is not acceptable. It is common for a failure in thedistribution system to cause a reduction in pressures resulting in a reduced nodal flow toconsumers. In order to predict the reduction in the levels of service as a result of thereduced flows, it is important to relate pressure changes with nodal outflows duringfailure events.Conventional network analysis methods do not allow the nodal outflow to be adjusted asa result of pressure reduction, as the models in general are demand driven. Modifiednetwork analysis is required where pressure dependent outflow functions are used.However many limitations associated with pressure dependent demand functions havebeen reported in the literature and these limitations restrict their applicability to realnetworks.In this paper a new method based on artificial neural networks is presented for relatingpressures and nodal outflows. The proposed method involves the detailed analysis ofseveral typical secondary networks, to provide sufficient data to train the neural network.Once trained the neural network is used to calculate the reduced outflows to nodes, basedon the secondary network type, time of failure and the resulting reduced pressure. Thepaper presents an example application to demonstrate the method and its strength overprevious methods. Includes 18 references, tables, figures.

Product Details

Edition: Vol. - No. Published: 04/01/2005 Number of Pages: 19 File Size: 1 file , 520 KB