TY - GEN
T1 - Centralized anaerobic digestion bioprocess plant identification and direct I-term neural control using second order learning
AU - Baruch, I. S.
AU - Saldierna, E. E.
AU - Galvan-Guerra, R.
PY - 2011
Y1 - 2011
N2 - The paper proposed to use a recurrent neural network model, and a real-time Levenberg-Marquardt algorithm of its learning for centralized modeling, identification and I-term control of an anaerobic digestion bioprocess, carried out in a fixed bed and a recirculation tank of a wastewater treatment system. The analytical model of the digestion bioprocess, used as process data generator, represented a distributed parameter system, which is reduced to a lumped system using the orthogonal collocation method, applied in four collocation points plus one- in the recirculation tank. The paper proposed to use centralized direct I-term adaptive neural control based on centralized neural identification of the plant. The comparative graphical simulation results of the digestion wastewater treatment system identification and control, exhibited a good convergence and precise reference tracking, giving slight priority to the direct control with respect to the optimal control applied.
AB - The paper proposed to use a recurrent neural network model, and a real-time Levenberg-Marquardt algorithm of its learning for centralized modeling, identification and I-term control of an anaerobic digestion bioprocess, carried out in a fixed bed and a recirculation tank of a wastewater treatment system. The analytical model of the digestion bioprocess, used as process data generator, represented a distributed parameter system, which is reduced to a lumped system using the orthogonal collocation method, applied in four collocation points plus one- in the recirculation tank. The paper proposed to use centralized direct I-term adaptive neural control based on centralized neural identification of the plant. The comparative graphical simulation results of the digestion wastewater treatment system identification and control, exhibited a good convergence and precise reference tracking, giving slight priority to the direct control with respect to the optimal control applied.
KW - Anaerobic digestion bioprocess plant
KW - Levenberg-Marquardt learning
KW - centralized neural identification
KW - direct I-term adaptive neural control
KW - distributed parameter system
KW - optimal control
KW - recurrent neural network
UR - http://www.scopus.com/inward/record.url?scp=84855778833&partnerID=8YFLogxK
U2 - 10.1109/ICEEE.2011.6106671
DO - 10.1109/ICEEE.2011.6106671
M3 - Contribución a la conferencia
AN - SCOPUS:84855778833
SN - 9781457710117
T3 - CCE 2011 - 2011 8th International Conference on Electrical Engineering, Computing Science and Automatic Control, Program and Abstract Book
BT - CCE 2011 - 2011 8th International Conference on Electrical Engineering, Computing Science and Automatic Control, Program and Abstract Book
T2 - 2011 8th International Conference on Electrical Engineering, Computing Science and Automatic Control, CCE 2011
Y2 - 26 October 2011 through 28 October 2011
ER -