Proactive Detection of Wastewater Overflows for Smart Sanitary Sewer Systems: Case Study in South Australia

AbstractSewage systems are built to carry contaminated wastewater from domestic discharge points to collection points for treatment. However, their capacity can be reduced by obstructions, displaced pipe joints, or broken pipes, creating abnormal hydraulic conditions. Wastewater overflows are a potential consequence of these abnormal conditions, which pose a direct threat to the environment and human health. This paper describes a permanent continuous monitoring system of a real sewage network using ultrasonic water level sensors for the purpose of blockage/choke detection, as installed in the suburb of Stonyfell, South Australia. From 62 available data sets collected over 1 year, two distinctive features of growing chokes were identified, including irregular peaks and durations that the water level remains irregularly high in the sewer maintenance holes. An early choke detection method was formulated based on the later feature, which continuously scans the near-real-time data to find time periods containing these abnormal water levels. Application of the methodology showed that the proposed method is effective in detecting possible chokes and overflow events before they occur. In most cases, the warning from the first detection is early enough to allow proactive maintenance attendance to be scheduled by the water utility.