Decentralized Adaptive Fuzzy-Neural Control of an Anaerobic Digestion Bioprocess Plant

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. Keywords— Decentralized control, direct adaptive control, indirect adaptive control, distributed parameter digestion bioprocess system, recurrent neural network model, hierarchical fuzzy neural identification and control.