Uppsala Vatten, which is the water supply provider in Uppsala Municipality, has a leakage of 14 percent in their water distribution network. This amounts to a yearly loss of 2.4 million cubic meters of processed drinking water and 1.8 GWh of wasted energy. Uppsala Vatten has a set goal of lowering the leakage from 14 to 10 percent by 2022. The company has around 40 wireless flow meters and is interested in using data analysis on flow data collected by these to find leaks more rapidly and thus decrease water loss. In this paper five algorithms for change detection were implemented and evaluated for the application of identifying leaks in water flow data. Implementation and testing of these algorithms on both real flow data and artificially created data was conducted to determine their suitability for the application and for relative comparison. Successful identification of leaks in real data was achieved for all five algorithms although the performance varied among them.
Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:uu-381976 |
Date | January 2019 |
Creators | Enander, Lukas |
Source Sets | DiVA Archive at Upsalla University |
Language | Swedish |
Detected Language | English |
Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
Format | application/pdf |
Rights | info:eu-repo/semantics/openAccess |
Relation | UPTEC ES, 1650-8300 ; 19 004 |
Page generated in 0.0015 seconds