The asymptotic local approach to change detection and model validation
Authors:
- A. BenvenisteABA. Benveniste
- M. BassevilleMBM. Basseville
- G. MoustakidesGMG. Moustakides
- 1 July 1987
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 32 (7) , 583-592
Abstract
We present a systematic approach for the design of change detection and model validation algorithms for dynamical systems. We show how to associate to any identification algorithm a change detection and a model validation procedure, which are optimal in some asymptotic sense. The foundations of our method go back to the asymptotic local approach in statistics, and our method generalizes this approach.Keywords
This publication has 13 references indexed in Scilit:
- Detection and diagnosis of abrupt changes in modal characteristics of nonstationary digital signals (Corresp.)IEEE Transactions on Information Theory, 1986
- Detecting changes in the ar parameters of a nonstationary arma processStochastics, 1986
- Single sample modal identification of a nonstationary stochastic processIEEE Transactions on Automatic Control, 1985
- Applications of a Kushner and Clark lemma to general classes of stochastic algorithmsIEEE Transactions on Information Theory, 1984
- Analysis of stochastic approximation schemes with discontinuous and dependent forcing terms with applications to data communication algorithmsIEEE Transactions on Automatic Control, 1980
- On the Invariance Principle for Nonstationary MixingalesThe Annals of Probability, 1977
- A Maximal Inequality and Dependent Strong LawsThe Annals of Probability, 1975
- Invariance principles for dependent variablesProbability Theory and Related Fields, 1975
- Asymptotic inference in stationary Gaussian time-seriesAdvances in Applied Probability, 1973
- Contiguity of Probability Measures1972