An artificial intelligence approach for optimizing pumping in sewer systems

摘要

This paper presents details of a fuzzy logic system developed for the control of sewer pumpingnstations for energy costs savings. This is part of an ongoing collaborative project between AngliannWater and the University of Sheffield. The model rules and operation are developed for onenrepresentative pumping station in order to enable the identification of potential benefits andninhibitors to Anglian Water. Results are included that demonstrate the potential for energyncost-savings by application to a single pumping station for dry weather flow conditions andnthrough comparison to current on/off switching rules. The fuzzy system is shown to be robustnto changes in flow pattern (using both modelled inflow data and real data from a flow survey), butnsensitive to changes in price structures. Application of a genetic algorithm (GA) search techniquenwas used to adjust the parameters that define the membership functions in the fuzzy rules, innorder to provide automated minimization of the energy costs towards an optimal solution. ThenGA system is shown to be transferable to another pumping station with different pump sizes,nwet well capacity and inflow pattern. The GA solution outperformed the base case in terms ofnenergy costs and switching totals.