Author(s): Mohamed Ibrahim M. Mohamed; Wenyan Wu
Linked Author(s):
Keywords: Leak and burst detection; Smart sensors; Unsupervised learning; WDS; Machine learning
Abstract: The current technology for detecting leak and burst events relies on offline techniques which collect loggers’data from multiple locations. We believe that detecting such events in real time, with smart sensors nodes, could improve monitoring operations and save operational costs. In this paper we analyse different machine learning techniques and investigate the ability to use them as real time intelligent event detection tools which use only the limited processing capabilities in the wireless sensor nodes. We are proposing a real-time leak detection approach which is light weight enough to run given the limited computing resources available in the nodes. Additionally, we evaluate the proposed approach against existing ones in terms of accuracy, and computational complexity.
Year: 2015