Original scientific paper
Neural Observer Based Hybrid Intelligent Scheme for Activated Sludge Wastewater Treatment
E. A. Hernandez-Vargas
orcid.org/0000-0002-3645-435X
; CINVESTAV, Unidad Guadalajara, Departamento de Control Automatico, Apartado Postal 31-438, Plaza la Luna, Guadalajara, Jal. Mexico, 45090
E. N. Sanchez
; CINVESTAV, Unidad Guadalajara, Departamento de Control Automatico, Apartado Postal 31-438, Plaza la Luna, Guadalajara, Jal. Mexico, 45090
J. F. Beteau
; Institute National Polytechnique de Grenoble, GIPSA-lab Department of control systems BP 46-38402 St-Martin d’Hères Cedex, France
C. Cadet
; Institute National Polytechnique de Grenoble, GIPSA-lab Department of control systems BP 46-38402 St-Martin d’Hères Cedex, France
Abstract
Activated sludge wastewater treatment plants have received considerable attention due to their efficiency to eliminate biodegradable pollution and their robustness to reject disturbances. Different control strategies have been proposed, but most of these techniques need sensors to measure process main variables. This paper presents a discrete-time recurrent high order neural observer (RHONO) to estimate substrate and biomass concentrations in an activated sludge wastewater treatment plant. The RHONO is trained on-line with an extended Kalman filter (EKF)-based algorithm. Then this observer is associated with a hybrid intelligent system based on fuzzy logic to control the substrate/biomass concentration ratio using the external recycle flow rate and the injected oxygen as control actions. The intelligent system and neural observer performance
is illustrated via simulations.
Keywords
Wastewater treatment; neural observer; process control; hybrid intelligent control
Hrčak ID:
40934
URI
Publication date:
29.9.2009.
Visits: 898 *