10.4122/1.1000001087
R\303\241duly, B.
B.
R\303\241duly
Gernaey, K.V.
K.V.
Gernaey
Capodaglio, A. G.
A. G.
Capodaglio
Mikkelsen, P. S.
P. S.
Mikkelsen
Henze, M.
M.
Henze
Rapid WWTP performance evaluation over a wide range of operating conditions using artificial neural networks
DTU Library, Technical University of Denmark (DTU)
2005
Conference presentation
ANN
modelling
performance evaluation
time series
WWTP
University Of Pavia, Dept. Of Hydraulic
Dept. Of Hydraulic
University Of Pavia
Lund University, Dept. Of Industrial Electrical Engineering
Dept. Of Industrial Electrical Engineering
Lund University
Technical University Of Denmark, Environment
Environment
Technical University Of Denmark
2005
en
10.4122/1.1000001088
text/xml
Wastewater treatment plants (WWTPs) are an essential component of the integrated urban water system. The simulation of the plants behaviour is becoming an essential tool for design, evaluation and everyday operation of the plants. Rather long influent time series containing a wide range of influent disturbances are needed to allow a simulation-based WWTP performance evaluation of sufficient quality, but this in turn requires long simulation times. The approach proposed in this paper combines an influent disturbance generator with a deterministic WWTP model for generating a limited sequence of training data (6 months of dynamic data). An artificial neural network (ANN) is then trained on the available WTTP input-output data, and is subsequently used to simulate the remainder of the influent time series (20 years of dynamic data) generated with the influent disturbance generator. It is demonstrated that the ANN reduces simulation time by a factor of 17, even when including the time needed for ANN training. ANN prediction of effluent BOD5 and total suspended solids was good when compared to deterministic WWTP model predictions (correlation coefficient > 0.95), whereas prediction of effluent ammonium and total nitrogen concentrations was less satisfactory (correlation coefficient > 0.70).