摘要：AbstractThe economic performance of distillation processes has been always addressed by techniques supporting and completing Model Predictive Control (MPC), which are known as Real Time Optimization (RTO). RTO, via simulation model, has been deeply studied and applied to distillation processes, nevertheless, the cost associated with the development of such online simulation models is often an obstacle for industries to change their operations. Hence, this work presents an unconventional RTO approach, named “analytical RTO”, which calculates the setpoint of manipulated variables according to operating strategy exploiting an analytical generalized formulation. The proposed RTO is built for a specific unit, that is a Propane-Propylene super-fractionator producing polymer grade Propylene (99.5%), and it is based on an offline simulation model developed in UniSim Design. Sensitivities analysis of the revenue with the manipulated variables is obtained with the simulation model and used to derive a simple, yet quite effective analytical RTO formulation, taking into account the fluidynamic limit of the unit studied. Comparing such an approach with the simulations, the results show a satisfactory match of the analytical estimations with the optimal points calculated by the rigorous model.
