Weighted least squares with EM Algorithn monitoring water distributions systems

Ye, G and Fenner, RA (2013) Weighted least squares with EM Algorithn monitoring water distributions systems. Journal of Water Resources Planning and Management. ISSN 0733-9496

Abstract

Flow measurement data at DMA (district meter area) level has the potential for burst detection in water distribution systems. This work investigates using a polynomial function fitted to the historic flow measurements based on a weighted least squares method for automatic burst detection. This approach when used in conjunction with an expectation-maximization (EM) algorithm can automatically select useful data from the historic flow measurements which may contain normal and abnormal operating conditions in the distribution network, e.g. water burst. Thus the model can estimate the normal water flow (non-burst condition) and hence the burst size on the water distribution system can be calculated from the difference between the measured flow and the estimated flow. The distinguishing feature of this method is that the burst detection is fully unsupervised, and the burst events which have occurred in the historic data do not affect the procedure and bias the burst detection algorithm. Experimental validation of the method has been carried out using a series of flushing events which simulate burst conditions to confirm that the simulated burst sizes are capable of being estimated correctly. This method is also applied to 8 real DMAs with known real burst events and the results of burst detections are shown to relate to the water company's records of pipeline reparation work.

Actions (login required)