Pressure determination in water distribution systems (WDS) is important because it generally drives the operational actions for\udleakage and failure management, backwater intrusion and demand control. This determination would ideally be done through\udpressure monitoring at every junction in the distribution system. However, due to limited resources, it is only possible to monitor\udat a limited number of nodes. To this end, this work explores the use of an Artificial Neural Network (ANN) to estimate pressure\uddistributions in a WDS using the available data at the monitoring nodes as inputs. The optimal subset of monitoring nodes are\udchosen through an entropy-based method. Finally, pressure values are compared to synthetic pressure measures estimated through\uda hydraulic model.
展开▼
