Semi-Batch Trajectory Control in Reduced Dimensional Spaces

A novel inferential strategy for controlling end-product quality properties using complete trajectories of manipulated variables is presented. Control through complete trajectory manipulation using empirical models only is possible by controlling the process in the reduce space (scores) of a latent variable model rather than in the real space of the manipulated variables. Model inversion and trajectory reconstruction is achieved by exploiting the correlation structure in the manipulated variable trajectories captured by a Partial Least Squares (PLS) model. The approach is illustrated with a condensation polymerisation example for the production of nylon. The data requirements for building the model are shown to be modest.