Water quality event detection and customer complaint clustering analysis in distribution systems

Abstract

Safe, clean drinking water is a foundation of society and water quality monitoring can contribute to ensuring this. A case study application of CANARY to historic data from a UK drinking water distribution system is described. Sensitivity studies explored appropriate choice of algorithmic parameter settings for a baseline site, performance was evaluated with artificial events and the system then transferred to all sites. Results are presented for analysis of 9 water quality sensors measuring six parameters and deployed in three connected District Meter Areas, fed from a single water source (service reservoir), for a one year period and evaluated using comprehensive water utility records with 86% of event clusters successfully correlated to causes (spatially limited to DMA level). False negatives, defined by temporal clusters of water quality complaints in the pilot area not corresponding to detections, were only approximately 25%. It was demonstrated that the software could be configured and applied retrospectively (with potential for future near real time application) to detect various water quality event types (with a wider remit than contamination alone) for further interpretation.

Determining the spatio-temporal relationship between water quality monitors in drinking water distribution systems

“…Determining optimal sensor deployment strategy [2] and how best to analyse the subsequent datasets are also major challenges. To date, water quality analytics has mainly focused on event detection [3][4][5] and little work has been done to understand how the spatio-temporal combination of water quality sensor data can be used to enhance DWDS water quality data analysis.…”

Development of a Water Quality Event Detection and Diagnosis Framework in Drinking Water Distribution Systems with Structured and Unstructured Data Integration

“…Abnormal conditions (e.g., water quality events) could cause changes in WDS measurements such as the pressure and flow rate [4]. In the event of a water quality accident, abnormal values will occur in the observed water quality measurements, such as turbidity, pH, electrical conductance, and temperature [5][6][7][8]. Recently, smart meters have been installed in WDSs [9][10][11][12][13][14][15] to capture data with a higher temporal resolution [16][17][18].…”

Water Quality Correction Within Water Distribution System

“…Unfortunately, the quality of transferred water can deteriorate within it, which is called secondary contamination [3]. The phenomenon of secondary water contamination in water supply systems widely appears around the world [4][5][6][7][8]. Causes of this phenomenon have different reasons, and factors affecting water contamination can be divided into several groups connected with: water, its treatment and entering into the water supply system, hydraulic conditions, and pipe age in water distribution system, piping material, and network structure [9][10][11][12][13][14].…”