Abstract
A machine learning approach to describing the dynamics of ultrafiltration performance in pretreatment of seawater reverse osmosis (RO) feedwater was explored via ensemble back propagation neural network (BPNN) model. The BPNN model was developed with Alopex evolutionary algorithm (AEA) optimization and AdaBoost strategy. The progression of ultrafiltration (UF) membrane resistance during both filtration and backwash, along with backwash efficiency were modeled via the ensemble BPNN-AEA approach relying on 422 days of operational data for an integrated SWRO UF-RO system. Model performance, for UF membrane resistance and backwash efficiency, evaluated over a wide range of operating conditions and coagulant dosing strategies, revealed excellent performance with a forecasting capability even for cases of temporally variable water quality. The performance level attained with the current machine learning modeling approach, which is particularly suited for handling the dynamics of UF operation, should prove useful for (a) determining UF performance deviation from intended baseline performance, (b) forecasting expected UF performance due to anticipated changes in water quality, and (c) providing a basis for model-based control of UF operation.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call