Discrete-time recurrent high order neural observer for activated sludge wastewater treatment

Author

Sanchez, E.N. ; Hernandez, E.A. ; Cadet, C. ; Beteau, J.F.

Author_Institution

CINVESTAV, Unidad Guadalajara, Guadalajara

fYear

2008

fDate

1-8 June 2008

Firstpage

1001

Lastpage

1005

Abstract

This paper presents a recurrent neural observer to estimate substrate and biomass concentrations in an activated sludge wastewater treatment. The observer is based on a discrete-time high order neural network (RHONN) trained on-line with an extended Kalman filter (EKF)-based algorithm. This observer is then associated with a hybrid intelligent system to control the substrate/biomass concentration ratio. The neural observer performance is illustrated via simulations.

Keywords

Kalman filters; discrete time systems; nonlinear filters; observers; recurrent neural nets; sludge treatment; wastewater treatment; activated sludge wastewater treatment; biomass concentrations; discrete-time recurrent high order neural observer; extended Kalman filter; hybrid intelligent system; substrate concentrations; Biomass; Bioreactors; Biosensors; Effluents; Electronic mail; Neural networks; Nitrogen; Recycling; State estimation; Wastewater treatment;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on

Conference_Location

Hong Kong

ISSN

1098-7576

Print_ISBN

978-1-4244-1820-6

Electronic_ISBN

1098-7576

Type

conf

DOI

10.1109/IJCNN.2008.4633921

Filename

4633921