Real-time learning and smart detection in water distribution systems

The increasing age and deterioration of drinking water mains is causing
an increasing frequency of pipe bursts. Not only are pipe repairs costly, bursts might also lead to contamination of the Dutch non-chlorinated drinking water, as well as damage to other above- and underground infrastructure. Detection and localization of pipe bursts have long been priorities for water distribution companies. Short-term water demand forecasting is a valuable tool in burst detection, as deviations between the forecast and actual water demand may indicate a new burst. Many of burst detection methods struggle with false positives due to non-seasonal water consumption as a result of e.g. environmental, economic or demographic exogenous influences, such as weather, holidays, festivities or pandemics. Finding a robust alternative that reduces the
false positive rate of burst detection and does not rely on data from exogenous processes is essential. There are existing methods for proactive leakage control and an exogenous nowcasting method for burst detection have been proposed.
However, better monitoring allows for easier identification of burst sites and faster response strategies, but heavily relies on sufficient insight in the network’s dynamics obtained from real-time flow and pressure sensor data. It is planned to use, e.g. a linearized state-space model of hydraulic networks to achieve optimal sensor placement. Observability Gramians can be used to identify the optimal
sensor configuration by maximizing the output energy of a given network state. This approach does not rely on model simulation of hydraulic burst scenarios or on burst sensitivity matrices, but instead determines optimal sensor placement solely from the model structure, taking into account the pressure and flow dynamics of the network.

Supervisors: Ming Cao, Jacquelien Scherpen and Doekle Yntema (Wetsus)
PhD: Ruixuan Qi