TY - GEN
T1 - Decentralized adaptive fuzzy-neural control of an anaerobic digestion bioprocess plant
AU - Baruch, Ieroham S.
AU - Galvan-Guerra, Rosalba
PY - 2009
Y1 - 2009
N2 - The paper proposed to use recurrent Fuzzy-Neural Multi-Model (FNMM) identifier for decentralized identification of a distributed parameter anaerobic wastewater treatment digestion bioprocess, carried out in a fixed bed and a recirculation tank. The distributed parameter analytical model of the digestion bioprocess is used as a plant data generator. It is reduced to a lumped system using the orthogonal collocation method, applied in three collocation points (plus the recirculation tank), which are used as centers of the membership functions of the fuzzyfied plant output variables with respect to the space variable. The local and global weight parameters and states of the proposed FNMM identifier are used to design hierarchical FNMM direct and indirect controllers. The comparative graphical simulation results of the digestion system direct and indirect control, obtained via learning, exhibited a good convergence, and precise reference tracking. The comparative numerical results, giving the final means squared error of control of each output variable showed that the indirect adaptive decentralized fuzzy-neural control outperformed the direct one, and the it outperformed the linearized proportional optimal control too.
AB - The paper proposed to use recurrent Fuzzy-Neural Multi-Model (FNMM) identifier for decentralized identification of a distributed parameter anaerobic wastewater treatment digestion bioprocess, carried out in a fixed bed and a recirculation tank. The distributed parameter analytical model of the digestion bioprocess is used as a plant data generator. It is reduced to a lumped system using the orthogonal collocation method, applied in three collocation points (plus the recirculation tank), which are used as centers of the membership functions of the fuzzyfied plant output variables with respect to the space variable. The local and global weight parameters and states of the proposed FNMM identifier are used to design hierarchical FNMM direct and indirect controllers. The comparative graphical simulation results of the digestion system direct and indirect control, obtained via learning, exhibited a good convergence, and precise reference tracking. The comparative numerical results, giving the final means squared error of control of each output variable showed that the indirect adaptive decentralized fuzzy-neural control outperformed the direct one, and the it outperformed the linearized proportional optimal control too.
KW - Decentralized control
KW - Direct adaptive control
KW - Distributed parameter digestion bioprocess system
KW - Hierarchical fuzzy neural identification and control
KW - Indirect adaptive control
KW - Recurrent neural network model
UR - http://www.scopus.com/inward/record.url?scp=79961188553&partnerID=8YFLogxK
M3 - Contribución a la conferencia
AN - SCOPUS:79961188553
SN - 9789899507968
T3 - 2009 International Fuzzy Systems Association World Congress and 2009 European Society for Fuzzy Logic and Technology Conference, IFSA-EUSFLAT 2009 - Proceedings
SP - 460
EP - 465
BT - 2009 International Fuzzy Systems Association World Congress and 2009 European Society for Fuzzy Logic and Technology Conference, IFSA-EUSFLAT 2009 - Proceedings
T2 - Joint 2009 International Fuzzy Systems Association World Congress, IFSA 2009 and 2009 European Society of Fuzzy Logic and Technology Conference, EUSFLAT 2009
Y2 - 20 July 2009 through 24 July 2009
ER -