Record nummer 2248891
Titel artikel Application of machine learning techniques to predict anomalies in water supply networks
Auteur(s) Vries, D. ; Akker, B. van den ; Vonk, E. ; Jong, W. de ; Summeren, J. van
Tijdschrifttitel Water science and technology : water supply / International Water Supply Association
Deel(Jaar)Nummer 16(2016)6
Paginering 1528 - 1535
Online full text
Op papier Haal het document, vind aanverwante informatie of gebruik andere SFX-diensten
Publicatie type Artikel
Taal Engels
Toelichting (Engels) Methods to improve the operational efficiency of a water supply network by early detection of anomalies are investigated by making use of the data streams from multiple sensor locations within the network. The water supply network is a demonstration site of Vitens, a Dutch water company that has several district metering areas where flow, pressure, electrical conductance and temperature are measured and logged online. Three different machine learning approaches are tested for their feasibility to detect anomalies. In the first approach, day-dependent support vector regression (SVR) models are trained for predicting the measurement signals and compared to straightforward models using mean and median estimates, respectively. Using SVRs or the averaged data as real-time pattern recognizers on all available signals, large leakages can be detected. The second approach utilizes adaptive orthogonal projections and reports an event when the number of hidden variables required to describe the streaming data to a user-defined degree (energy-level threshold) increases. As a third approach, (unsupervised) clustering techniques are applied to detect anomalies and underlying patterns from the raw data streams. Preliminary results indicate that the current dataset is too limited in the amount of events and patterns to harness the potential of these techniques.
Betrokken instanties Vitens
KWR, Watercycle Research Institute
Er zijn nog geen reacties. U kunt de eerste schrijven!
Schrijf een reactie

To support researchers to publish their research Open Access, deals have been negotiated with various publishers. Depending on the deal, a discount is provided for the author on the Article Processing Charges that need to be paid by the author to publish an article Open Access. A discount of 100% means that (after approval) the author does not have to pay Article Processing Charges.

For the approval of an Open Access deal for an article, the corresponding author of this article must be affiliated with Wageningen University & Research.