Analysis of Leaks in Water Pipe Networks Using a Statistical Data Analysis Method
In this paper the potential of the Principal Component Analysis(PCA) technique for the application of detecting leaks in water pipe networks was evaluated. For this purpose the PCA was conducted to evaluate the relevance of the calculated statistical outliers of a PCA model utilizing the recorded inflows of DMAs(District Metered Areas) and the records of leak repairs of a case study water pipe network. The PCA technique was enhanced by using the flow data in a time window from the original 24 hour flow data so that the effective outlier detection rate was maximized. Consideration on how to apply the parameters in the practical applications was also presented. The developed algorithm may be applied in determining whether further leak detection field work for DMAs needs to be performed if the flow data of a previous day resulted in an outlier of the PCA model.
Keywords - Principal Component Analysis, DMA, water pipe network, leak detection, computational algorithm