Assessment of Control Loop Performance

For processes described by linear transfer functions with additive disturbances, the best possible control in the mean square sense is realized when a minimum variance controller is implemented. It is shown that an estimate of the best possible control can be obtained by fitting a univariate time series to process data collected under routine control. No ‘identifiabuity’ constraints need be imposed. The use of this technique is demonstrated with pilot plant and production data. Pour les procedes decrits par des fonctions de transfert lineaires avec des perturbations additives, le meilleur controle possible au sens des moindres carres s'obtient avec un regulateur a variance minimum. On montre qu'on peut obtenir une estimation du meilleur controle possible en adaptant une serie chronologique univariee pour traiter des donnees recueillies lors d'un retrocontrole de routine. Il n'est pas necessaire d'imposer des contraintes d'«identificabilite». L'utilisation de cette technique est decrite par des donnees d'une usine pilote et des donnees de production.

[1]  John F. MacGregor,et al.  Some Recent Advances in Forecasting and Control , 1968 .

[2]  H. Akaike.  Fitting autoregressive models for prediction , 1969 .

[3]  H. Akaike.  Power spectrum estimation through autoregressive model fitting , 1969 .

[4]  Björn Wittenmark,et al.  On Self Tuning Regulators , 1973 .

[5]  George E. P. Box,et al.  Parameter Estimation with Closed-Loop Operating data , 1975 .

[6]  Warren R. DeVries,et al.  Evaluation of process control effectiveness and diagnosis of variation in paper basis weight via multivariate time-series analysis , 1978 .

[7]  G. Box,et al.  On a measure of lack of fit in time series models , 1978 .

[8]  R. Shinnar,et al.  Design of Sampled Data Controllers , 1979 .

[9]  R. Baillie.  The Asymptotic Mean Squared Error of Multistep Prediction from the Regression Model with Autoregressive Errors , 1979 .

[10]  John F. MacGregor,et al.  Self-Tuning and Adaptive Controllers: An Application to Catalytic Reactor Control , 1980 .

[11]  W. Fuller,et al.  Properties of Predictors for Autoregressive Time Series , 1981 .

[12]  John F. MacGregor,et al.  An overview of discrete stochastic controllers: Generalized PID algorithms with dead-time compensation , 1982 .

[13]  J. Macgregor,et al.  Duality Between the Control of Processes Subject to Randomly Occurring Deterministic Disturbances and ARIMA Stochastic Disturbances , 1984 .

[14]  Genshiro Kitagawa,et al.  Statistical Analysis of the AR Type Ship’s Autopilot System , 1984 .