Centralized Indirect Control of an Anaerobic Digestion Bioprocess Using Recurrent Neural Identifier

Authors:
Ieroham S. Baruch;Rosalba Galvan-Guerra;Boyka Nenkova
Affiliations:
Department of Automatic Control, CINVESTAV-IPN, Mexico D.F., Mexico C.P. 07360;Department of Automatic Control, CINVESTAV-IPN, Mexico D.F., Mexico C.P. 07360;Institute of Information Technologies, BAS, , Sofia, Bulgaria 1113
Venue:
AIMSA '08 Proceedings of the 13th international conference on Artificial Intelligence: Methodology, Systems, and Applications
Year:
2008

Citing 7
Cited 0

Comparison of linear, nonlinear and neural-network-based adaptive controllers for a class of fed-batch fermentation processes

Automatica (Journal of IFAC)
Orthogonal spline collocation methods for partial differential equations

Journal of Computational and Applied Mathematics - Special issue on numerical analysis 2000 Vol. VII: partial differential equations
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Proper orthogonal decomposition based optimal neurocontrol synthesis of a chemical reactor process using approximate dynamic programming

Neural Networks - 2003 Special issue: Advances in neural networks research — IJCNN'03
Adaptive recurrent neural network control of biological wastewater treatment: Research Articles

International Journal of Intelligent Systems - Soft Computing for Modeling, Simulation, and Control of Nonlinear Dynamical Systems
Diagrammatic derivation of gradient algorithms for neural networks

Neural Computation
Adaptive-critic based optimal neuro control synthesis for distributed parameter systems

Automatica (Journal of IFAC)

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper proposed to use a Recurrent Neural Network Model (RNNM) and a dynamic Backpropagation learning for centralized identification of an anaerobic digestion bioprocess, carried out in a fixed bed and a recirculation tank of a wastewater treatment system. The anaerobic digestion bioprocess represented a distributed parameter system, described by partial differential equations. The analytical model is simplified to a lumped ordinary system using the orthogonal collocation method, applied in three collocation points, generating data for the neural identification. The obtained neural state and parameter estimations are used to design an indirect sliding mode control of the plant. The graphical simulation results of the digestion wastewater treatment indirect control exhibited a good convergence and precise reference tracking.