On batch process control using feature extraction with application to a gravimetric blender

Formentin S., A. Cologni, F. Previdi, S.M. Savaresi

In this paper, a data-driven control approach for batch processes based on feature extraction is proposed. In this strategy, a model of the system dynamics is not needed and the issue of adapting to different operating conditions is recast into a simple controller design problem. Throughout the paper, the proposed algorithm will be described in detail with the help of an experimental gravimetric blender example.