Abstract
The Principal Components Regression method is adapted for automatic process control synthesis. The modified method ensures that the constraints imposed on the controlled variables are satisfied as the control and disturbing actions vary randomly. Conventional methods of compressing information into a space of a lower dimensionality are adapted for constrained controlled variables. A simple numerical example is provided to illustrate the synthesis of a linear control system for a given model process.
Similar content being viewed by others
REFERENCES
Chen, G. and McAvoy, T.J., Process Control Utilizing Data Based Multivariate Statistical Models, Can. J. Chem. Eng., 1996, vol. 74, no. 11, p. 1010.
Malthouse, E.C., Tamhane, A.C., and Mah, R.S.H., Non-linear Partial Least Squares, Comput. Chem. Eng., 1997, vol. 21, no. 8, p. 875.
Qin, S.J. and McAvoy, T.J., Nonlinear PLS Modelling Using Neural Networks, Comput. Chem. Eng., 1992, vol. 16, no. 4, p. 379.
Meidell, T. and Skogestad, S., Composition Estimator in a Pilot-Plant Distillation Column Using Multiple Temperatures, Ind. Eng. Chem. Res., 1991, vol. 30, no. 7, p. 2555.
Dovi', V.G., Reverberi, A.P., and Maga, L., Reconciliation of Process Measurements When Data Are Subject to Detection Limits, Chem. Eng. Sci., 1997, vol. 52, no. 17, p. 3047.
Martens, H. and Naes, T., Multivariate Calibration, London: Wiley, 1989.
Piovoso, M.J. and Kosanovich, K.A., The Use of Multivariate Statistics in Process Control, The Control Handbook, Levine, M.S., Ed., New York: CRC, 1994.
Shumway, R.H., Azari, A.S., and Johnson, P., Estimating Mean Concentrations under Transformation for Environmental Data with Detection Limits, Technometrics, 1989, vol. 31, no. 3, p. 347.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Maga, L., Meshalkin, V.P., Dovi', V.G. et al. Process Control System Synthesis under Constraints Imposed on Controlled Variables. Theoretical Foundations of Chemical Engineering 36, 389–394 (2002). https://doi.org/10.1023/A:1019860018741
Issue Date:
DOI: https://doi.org/10.1023/A:1019860018741