1988
DOI: 10.1021/ie00081a016
|View full text |Cite
|
Sign up to set email alerts
|

An adaptive estimation algorithm for inferential control

Abstract: An estimator relationship for inferring infrequently measured process outputs, from other more rapidly sampled secondary outputs, is derived. The structure of the estimator is not application dependent, and its parameters can be continuously estimated and updated. As a result, slow variations in plant or disturbance characteristics can be tracked. Closed-loop control schemes using the estimated output data are shown to exhibit superior performance over those using the slowly measured output data. In contrast t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0
3

Year Published

1992
1992
2001
2001

Publication Types

Select...
3
3

Relationship

0
6

Authors

Journals

citations
Cited by 34 publications
(7 citation statements)
references
References 5 publications
0
4
0
3
Order By: Relevance
“…The estimation loop can be closed, however, by feeding infrequent off-line measurements of the state variables into the estimator. Instead of applying this methodology to a Kalman filter, Guilandoust et al (1988) and Tham et al (1988) utilized a different approach. They formulated a linear black-box model with unknown parameters, relating the state variables to infrequent off-line and frequent on-line measurements.…”
Section: Aiche Journalmentioning
confidence: 99%
“…The estimation loop can be closed, however, by feeding infrequent off-line measurements of the state variables into the estimator. Instead of applying this methodology to a Kalman filter, Guilandoust et al (1988) and Tham et al (1988) utilized a different approach. They formulated a linear black-box model with unknown parameters, relating the state variables to infrequent off-line and frequent on-line measurements.…”
Section: Aiche Journalmentioning
confidence: 99%
“…To achieve this objective when the process is time varying, adaptive multirate system identification strategies need to be used to formally accommodate the two or more sampling rates that exist in such a scenario. Guilandoust et al (1987Guilandoust et al ( , 1988 proposed an adaptive multirate inferential estimation algorithm in state space and transfer function form. Lu and Fisher (1990) have formulated the multirate estimation problem such that the working equations explain the inferential relationships in a more fundamental way and thus have formally proved the convergence properties of such an inferential control algorithm.…”
Section: Introductionmentioning
confidence: 99%
“…En cuanto a la introducción de un predictor para subsanar la falta de información de la salida en algunos instantes de control, algunos autores ya han utilizado la técnica de control inferencial (véase [20,33,36]) utilizando un modelo del proceso para estimar y realimentar las salidas que no se pueden medir. En estos trabajos se alimenta el controlador bien con una estimación de la salida en bucle abierto o bien directamente con la salida medida cuandoésta está disponible.…”
Section: Control Con Medidas Escasasunclassified
“…La dinámica del error de predicción en el instante de medición queda simplificada a 20) donde el error de estimación en bucle abierto ( x[t|t − 1]) se puede poner en función de la información del instante anterior como…”
Section: Error De Predicciónunclassified
See 1 more Smart Citation