N. Delgrange et al., NEURAL NETWORKS FOR PREDICTION OF ULTRAFILTRATION TRANSMEMBRANE PRESSURE - APPLICATION TO DRINKING-WATER PRODUCTION, Journal of membrane science, 150(1), 1998, pp. 111-123
Modelling of ultrafiltration plants for drinking water production appe
ars as a necessary step before plants control and supervisory. It firs
t requires a better knowledge about membrane fouling by natural waters
. The phenomena involved are very complex, because of the nature of th
e fluid concerned: water. Thus up to now phenomenological model cannot
be applied for resource waters. Because of their properties, new mode
lling tools called neural networks seem to be a promising way to model
complex phenomena and therefore to be applied to water treatment. In
the present study a neural network is used to model the time evolution
of transmembrane pressures for ultrafiltration membranes applied to d
rinking water production. Different network structures and architectur
es have been elaborated and evaluated with the aim of computing the pr
essure at the end of a filtration cycle and after the next backwash. F
or some of these networks a very good accuracy is obtained for both pr
essures predictions. The inlets are permeate flow rate, turbidity duri
ng the cycle and pressure measurements at the cycle start and at the e
nd of the previous cycle. These networks are able to model the effect
of both reversible and irreversible fouling on pressures even if no in
let parameter concerning organic matters is considered. (C) 1998 Elsev
ier Science B.V. All rights reserved.