Control of a loop polymerization reactor using neural networks

or multivariable non linear predictive control implementations, a hybrid-neural model (lumped model) was successfully used for modeling a loop-tubular polymerization reactor (a lumped or distributed model, depending on recycle ratio). Bifurcation diagrams were computed in order to investigate the agreement between process and model, of paramount importance for model based controller implementation purposes. Performance was evaluated considering the nonlinear model predictive control of both a loop tubular reactor (lumped) SISO problem and a tubular reactor (distributed) MIMO problem.