Recursive data-based prediction and control of batch product quality

In typical batch and semibatch processes, process/feedstock disturbances occur fiequently and on-line measurements of product quality uariables are not auailable. As a result, most batch processes have not been able to achieue tight quality control. Empirical, data-driven approaches are ueiy attractive for dealing with this problem because of the difficulties associated with developing accurate process models from first principles. An approach for recursive on-line quality prediction was deueloped around data-based model structures. Techniques designed to incorporate the predictive models into on-line monitoring and control of batch product quality were also examined. The proposed control approach can be viewed as shrinking-horizon model-predictiue control based on empirical models. The effectiveness of the proposed prediction and control methods are illustrated by using an industrially releuant simulated polymerization example.