Pattern Recognition of the Household Water Consumption through Signal Analysis

Authors

Abstract

This paper presents the initial results of a research project that aims to develop a method for losses/leakage detection and household water consumption characterization through the detailed patterns analysis of signals generated by water meters. The Department of Civil Engineering (University of Coimbra) supports the research as part of a PhD Project. An experimental facility is used for signals acquisition and data analysis will be performed by using a pattern recognition algorithm that will identify the hydraulic devices in use. It is intended to develop and test some algorithm structures at various plumbing configuration forms to find the best one. In a second phase, a consumption analysis will be carried out using that algorithm to test its efficiency in inhabited houses.
The expectation is to develop an efficient water monitoring tool that helps the users to follow-up and to control the water consumption using a computer or
even a mobile device.

Keywords

pattern recognition, signal processing, monitoring household water

Subject

Intelligent Signal Processing; pattern recognition

Conference

DOCEIS 2011, February 2011