Control of nonlinear chemical processes using dynamic neural models
and feedback linearization
H.A.B. te Braake,
H.J.L. van Can, J.M.A. Scherpen, H.B. Verbruggen,
Computers Chem. Engng , Vol. 22, 7-8 (1998) 1113-1127.
Abstract:
Black-box modeling techniques based on artificial neural networks are
opening new horizons for modeling and controlling nonlinear processes in
biotechnology and chemical process industries. The link between dynamic
process models and actual process control is provided by the concept of
model based control (MBC), e.g. Internal Model Control (IMS) or Model Based
Predictive Control (MBPC). To avoid time consuming calculations, feedback
linearization techniques can be used to linearize the nonlinear process
model. The resulting linear model then can be used in a linear MBC scheme,
allowing standard linear control techniques to be applied. Two methods of
input/output feedback linearization are described in combination with the
use of neural process models. The exact input/output feedback linearization
and the approximate input/output feedback linearization. The proposed
methods are applied to a MISO (multi-input single-output) laboratory scale
pressure process, which shows good results compared to conventional linear
techniques.
Click HERE to receive a
preliminary
version of the paper as a gzipped postscript file (372Kb).
Click HERE for a
preliminary
version of the paper as a pdf file (579Kb). (Note: the plots may come out
badly.)
A hard copy of the paper is available upon request.