论文信息 - Synchronization of Multivariate Captors with an Autoadaptive Neural Method

Synchronization of Multivariate Captors with an Autoadaptive Neural Method

Before any multivariate analysis scheme (using typicaly simultaneous measurements) it is useful to readjust in time each measurement so that each one refer to the same element of the model. This problem arises frequently in the modelization of an industrial process. It is sometimes possible to propose a dynamic model after a microscopic study of displacements of matter. However such a study is very complex and cannot be conceived by a machine analysis of the data.In this article we present a practical self-adapting methodology which automates the synchronization of captors. This method use a recurrent neural network for the self auto-adaptivity of the synchronization. This network is model and tune automaticaly by an initialization process based on the local stationary phenomena appearing in measurements.

Jérôme Lacaille | J. Lacaille

[1] Masanao Aoki,et al. State Space Modeling of Time Series , 1987 .

[2] A. Lewbel,et al. Testing the Rank and Definiteness of Estimated Matrices with Applications to Factor, State-Space and ARMA Models , 1992 .

[3] R. E. Kalman,et al. Contributions to the Theory of Optimal Control , 1960 .

[4] Nicholas P. Jewell,et al. Canonical Correlations of Past and Future for Time Series: Bounds and Computation , 1983 .

[5] H. Akaike. Canonical Correlation Analysis of Time Series and the Use of an Information Criterion , 1976 .

[6] T. W. Anderson,et al. An Introduction to Multivariate Statistical Analysis , 1959 .

[7] J. Schmee. An Introduction to Multivariate Statistical Analysis , 1986 .

[8] U. Desai,et al. A realization approach to stochastic model reduction and balanced stochastic realizations , 1982, 1982 21st IEEE Conference on Decision and Control.

[9] Nicholas P. Jewell,et al. Canonical Correlations of Past and Future for Time Series: Definitions and Theory , 1983 .