| Recursive Neuro-Fuzzy Algorithm for Flow Prediction and Pump On-Off Minimization |
|---|
|
학술지명 Springer
저자 장상복,신강욱,홍성택,이호현,전명근
발표일 2014-07-01
|
|
In the water treatment process, a main objective is to improve thewater quality and also minimize the production costs. To achieve these, anintegrated monitoring and control system has been established through flowprediction and pump scheduling. This paper proposes a new integrated solutionfor predictions and optimal pump control by learning algorithms. Flowprediction has usually been studied for daily or monthly estimation, which isinsufficient for real-time control of a water treatment plant (hereafter WTP). Anhourly based estimator is proposed to track the steady change of flow demand.Unlike electricity, water can be stored in huge tanks for more than a dozenhours, which can be used for saving energy and increasing water quality. Pumpon/off minimization is considered to improve the water quality. If influent waterto a water treatment plant varies, then output turbidity and particles areincreasing, which could possibly be supplied to citizens. The proposed on/offminimization algorithm is expected to prevent those particles from leaking andto secure public health. |