Mid-course control of particle size distribution in emulsion polymerization using a hybrid model

This work proposes a practical approach to control the particle size distribution in seeded semi-batch emulsion polymerization. In this approach, initially an offline optimization is performed and the resulting monomer feed trajectory is implemented at the plant up to the predefined mid-course point of the batch. Frequent measurements are used to estimate the lumped states of the system using a state estimator. The estimated states and the measured PSD at the mid-course of the process are used as the initial condition for a re-optimization which is performed to obtain the trajectory of the monomer feed from the mid-course up to the end of the batch. In this re-optimization, a hybrid model which comprises the Fokker-Planck equation model of emulsion polymerization and a data-based component that corrects the predictions of the Fokker-Planck model during the re-optimization is used.