An accelerometer-based leak detection system

Aging infrastructures, specifically pipelines, that were installed decades ago and currently operating under poor conditions are highly susceptible to the threat of leaks, which pose economic, health, and environmental risks. For example, in the year 2009, the state of Ontario lost 25% of its water supply solely due to leaks. Therefore, a need arises to develop an approach that allows condition monitoring and early intervention. This article proposes a model for a real-time monitoring system capable of identifying the existence of single event leaks in pressurized water pipelines. The model proposes that wireless accelerometers be placed within the network on the exterior of the valves connecting the pipelines. To test the viability of the proposal, experiments were performed on one-inch cast iron pipelines, one-inch and two-inch PVC pipelines using single event leaks and the results were displayed. The vibration signal derived from each accelerometer was assessed and analyzed to identify the Monitoring Index (MI) at each sensor. The data collected from experimentation were analyzed using support vector machines (SVM), Decision Tree (DT), and Naive Bayes (NB). A leak threshold was determined such that if the signal increased above the threshold, a leak status is identified. The developed models showed promising results with 98.25% accuracy in distinguishing between leak states and non leak states. The proposed model is aimed at presenting novel approaches to providing municipalities with an affordable real-time monitoring system capable of aiding them in early detection and facilitating the repair process of leaks. (C) 2018 Elsevier Ltd. All rights reserved.