An Accelerometer-Based Real-Time Monitoring and Leak Detection System for Pressurized Water Pipelines

Aging infrastructure, and pipelines installed and operated under poor conditions in pressurized drinking water networks are highly susceptible to the threat of leaks; these leaks pose economical, health, and environmental threats. To allow early repair and condition monitoring, multiple researchers tried to address the issue of leak detection and leak location pinpointing using either biological, hardware-based, or software-based solutions. The previous models came short in identifying practical and cost-effective models for combining real-time monitoring, identification, and location predicting. The research presented in this article proposes a model for a real time monitoring system capable of pinpointing the location of single event leaks in pressurized water pipelines. The model relies on wireless accelerometers placed within the network on the exterior of the pipelines. The vibration signals derived from each accelerometer was assessed and analyzed by the model to identify the monitoring index (MI) at each sensor on the pipeline. A leak was identified when the value of the monitoring index spiked above the acceptable ranges identified through an experimental procedure for each sensor. The value of the monitoring index on the left and right of the suspected leak is processed and utilized along with the distance between the two sensors. This allowed the model to identify the original source of the signal i.e. the leak location within a maximum range of ± 25 cm. The leak location was determined by means of a regression equation developed from experimental data for each sensor. 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.