Water lost through leakage from water distribution networks is often appreciable. As pressure increases on water resources, there is a growing emphasis for water service providers to minimize this loss. The objective of the work presented in this paper was to assess the online application and resulting benefits of an artificial intelligence system for detection of leaks/bursts at district meter area (DMA) level. An artificial neural network model, a mixture density network, was trained using a continually updated historic database that constructed a probability density model of the future flow profile. A fuzzy inference system was used for classification; it compared latest observed flow values with predicted flows over time windows such that in the event of abnormal flow conditions alerts are generated. From the probability density functions of predicted flows, the fuzzy inference system provides confidence intervals associated with each detection, these confidence values provide useful information for filtering and ranking alerts. Additionally an accurate estimate of abnormal flow magnitude is produced to further aid in ranking of alerts. A water supply system in the U.K. was used for a case study with near real-time flow data provided by general packet radio service. The online burst alert system was constructed to operate alongside an existing flat-line alarm system, and continuously analyze a set of 144 DMAs every hour. The new system identified a number of events and alerts were raised prior to their detection in the control room; either through flat-line alarms or customer contacts. Examples are given of alert correlation with burst reports and subsequent mains repairs for a 2-month trial period. Forty four percent of alerts were found to correspond to bursts confirmed by repair data or customer contacts, 32% of alerts were confirmed as unusual short-term demand from manual analysis, 9% were related to known industrial events, and only 15% were ghosts. The results indicate that the system is an effective and viable tool for online burst detection in water distribution systems with the potential to save water and improve customer service.

The sampling frequency and quantity of time series data collected from water distribution systems has been increasing in recent years, giving rise to the potential for improving system knowledge if suitable automated techniques can be applied, in particular, machine learning. Novelty (or anomaly) detection refers to the automatic identification of novel or abnormal patterns embedded in large amounts of “normal” data. When dealing with time series data (transformed into vectors), this means abnormal events embedded amongst many normal time series points. The support vector machine is a data-driven statistical technique that has been developed as a tool for classification and regression. The key features include statistical robustness with respect to non-Gaussian errors and outliers, the selection of the decision boundary in a principled way, and the introduction of nonlinearity in the feature space without explicitly requiring a nonlinear algorithm by means of kernel functions. In this research, support vector regression is used as a learning method for anomaly detection from water flow and pressure time series data. No use is made of past event histories collected through other information sources. The support vector regression methodology, whose robustness derives from the training error function, is applied to a case study.

This paper presents research into the application of artificial neural networks (ANNs) for analysis of data from sensors measuring hydraulic parameters (flow and pressure) of the water flow in treated water distribution systems. Two neural architectures (static and time delay) are applied for time series pattern classification from the perspective of detecting leakage. Results are presented using data from an experimental site in a distribution system of a UK water company in which bursts were simulated by hydrant flushing. Field trials have shown how ANNs can be used effectively for a leakage detection task. Both static and time delay ANNs learned patterns of leaks/bursts. The time delay neural network showed improved performance over the static network. It is concluded that the effectiveness of an ANN in discovering relationships within the data is dependent upon two key factors: availability of sufficient exemplars and data quality.

This paper describes how hydraulic and water quality data from a distribution network may be used to provide a more efficient leakage management capability for the water industry. The research presented concerns the application of artificial neural networks to the issue of detection and location of leakage in treated water distribution systems. An architecture for an Artificial Neural Network (ANN) based system is outlined. The neural network uses time series data produced by sensors to directly construct an empirical model for predication and classification of leaks. Results are presented using data from an experimental site in Yorkshire Water's Keighley distribution system.

This paper presents a method to identify ‘optimal’ locations of pressure sensor instruments for the detection of leak/burst events and the results of a set of field trials conducted to evaluate the approach. The identification method is based on complete enumeration studies using hydraulic model simulations of a wide range of burst events and evaluating the response to each event at all possible monitoring points. The field trials simulated leak/burst events through the opening of fire hydrants within a selected District Metered Area (DMA), five different hydrants were opened systematically in the DMA to simulate different leak/burst events. By installing pressure instrumentation at different locations in the DMA, an understanding of how accurately the model methodology can determine sensitivity of instrument location can be obtained. Prior to and during the hydrant openings pressure data was collected at eight different instrument locations within the DMA. These pressure instruments were installed to cover different model predicted sensitivities and to provide good spatial coverage. The results show that pressure instrumentation location is crucial to sensitivity and that the modelling methodology is able to predict instrument location sensitivity to leak/burst events and thus offer an improvement over current industry practice for instrument deployment. It should be noted that this field application made use of current UK standard models, with no additional calibration or updating.