Neural Networks Based Model Predictive Control for a Lactic Acid Production Bioprocess

摘要

This work deals with the design and analysis of a nonlinear model predictive control (NMPC) strategy for a lactic acid production that is carried out in two continuous stirred bioreactors sequentially connected. The adaptive NMPC control structure is based on a dynamical neural network used as on-line approximator to learn the time-varying characteristics of process parameters. Minimization of a cost function depending on control inputs is realised using the Levenberg-Marquardt numerical optimisation method. The effectiveness and performance of the proposed control strategy is illustrated by numerical simulations applied in the case of a lactic fermentation bioprocess for which kinetic dynamics are strongly nonlinear, time varying and completely unknown.