Premium
Using Neural Networks to Predict Treatment Process Performance
Author(s) -
Veerapaneni Srinivas Vasu,
Budd George,
Bond Rick,
Horsley Mike
Publication year - 2010
Publication title -
journal ‐ american water works association
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.466
H-Index - 74
eISSN - 1551-8833
pISSN - 0003-150X
DOI - 10.1002/j.1551-8833.2010.tb10083.x
Subject(s) - artificial neural network , boiler feedwater , ultrafiltration (renal) , microfiltration , computer science , process (computing) , fouling , process engineering , membrane fouling , artificial intelligence , machine learning , engineering , waste management , chromatography , membrane , chemistry , boiler (water heating) , biochemistry , operating system
This article discusses the application of a simple artificial neural network (ANN) model to predict microfiltration/ultrafiltration (MF/UF) performance with reasonable accuracy using data typically gathered online in an MF/UF facility. By developing a site‐specific ANN model, operators of MF/UF facilities could predict the performance of critical parameters such as transmembrane pressure (TMP) and plan accordingly. For instance, when the model predicts a higher rate of fouling based on feedwater quality, operating conditions could be modified to reduce the rate of increase of TMP, thereby reducing the required cleaning frequency of MF/UF systems.