Near real-time detection of blockages in the proximity of combined sewer overflows using evolutionary ANNs and statistical process control

Abstract

Blockages are a major issue for wastewater utilities around the world, causing loss of service, environmental pollution, and significant clean-up costs. Increasing telemetry in combined sewer overflows (CSOs) provides the opportunity for near real-time data-driven modelling of wastewater networks. This paper presents a novel methodology, designed to detect blockages and other unusual events in the proximity of CSO chambers in near real-time. The methodology utilises an evolutionary artificial neural network (EANN) model for short-term CSO level predictions and statistical process control (SPC) techniques to analyse unusual level behaviour. The methodology was evaluated on historic blockage events from several CSOs in the UK and was demonstrated to detect blockage events quickly and reliably, with a low number of false alarms. HIGHLIGHTS Development of a novel real-time data-driven blockage detection system.; Two blockage detection techniques: EANN discrepancy-based analysis and statistical trend-based analysis.; Utilising only CSO level data, rainfall data and rainfall nowcasts.; Testing on real case studies demonstrates timely and reliable performance.;

Keywords

• blockage detection
• combined sewer overflow
• evolutionary artificial neural network
• radar rainfall nowcasts
• statistical process control