Anaerobic digestion process identification using recurrent neural network model

This paper proposes the use of a Recurrent Neural Network Model (RNNM) for decentralized and centralized identification of an aerobic digestion process, carried out in a fixed bed and a recirculation tank anaerobic wastewater treatment system. The analytical model of the digestion bioprocess represented a distributed parameter system, which is reduced to a lumped system using the orthogonal collocation method, applied in three collocation points. The proposed decentralized RNNM consists of four independently working Recurrent Neural Networks (RNN), so to approximate the process dynamics in three different measurement points plus the recirculation tank. The RNN learning algorithm is the dynamic Backpropagation one. The comparative graphical simulation results of the digestion wastewater treatment system approximation, obtained via decentralized and centralized RNNM learning, exhibited a good convergence, and precise plant variables tracking.