zbMATH — the first resource for mathematics

Quantification of prior knowledge about global characteristics of linear normal model. (English) Zbl 0556.93070
The Bayesian approach to system identification requires from the user to collect and express his prior information about the identified system. The paper presents a way in which a global prior knowledge can be quantified. Two simple cases, pulse response smoothness and knowledge of the static gain of a system modelled by mixed autoregressive-regressive model, are elaborated in detail. These cases which are of practical importance illustrate main steps in the quantification. The significant and favourable effect of this built-in prior information on the start of self-tuning control is demonstrated on an example.

93E12 Identification in stochastic control theory
62A01 Foundations and philosophical topics in statistics
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
93C05 Linear systems in control theory
93C40 Adaptive control/observation systems
Full Text: EuDML
[1] J. Böhm A. Halousková M. Kárný, V. Peterka: Simple LQ selftuners. Preprints 9th IFAC World Congress, Budapest 1984.
[2] G. J. Biermann: Factorization Methods for Discrete Sequential Estimation. Academic Press, New York 1977.
[3] M. H. De Groot: Optimal Statistical Decision. McGraw-Hill, New York, 1970.
[4] B. Hanuš: Ein einfaches Programm zur Ermittlung von Übergangscharakteristiken. ”XVIII. Interactionales Ilmenau”, Ilmenau 15.-19. 10. 1973. Ilmenau, TH 1973, No. 3, 25-27.
[5] M. Kárný: Bayesian estimation of model order. Problems Control Inform. Theory 9 (1980), 1, 33-46. · Zbl 0444.93046
[6] M. Kárný: Algorithms for determining the model structure of a controlled system. Kybernetika 19 (1983), 2, 164-178.
[7] R. Kulhavý, M. Kárný: Tracking of slowly varying parameters by directional forgetting. Preprints 9th IFAC World Congress, Budapest 1984.
[8] V. Peterka: Subjective probability approach to real-time identification. Preprints 4th IFAC Symposium on Identification and System Parameter Estimation, Tbilisi, USSR, 3 (1976), vol. 3, 83-96.
[9] V. Peterka: Experience accumulation for decision making in multivariate time series. Problems Control Inform. Theory 7 (1978), 3, 143-159. · Zbl 0396.93045
[10] V. Peterka: Bayesian approach to system identification. Trends and Progress in System Identification (P. Eykhoff, IFAC Series for Graduates, Research Workers and Practicing Engineers 1 (1981). · Zbl 0451.93059
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.