RECURRENT REPRESENTATION FOR NON-STATIONARY PARAMETER ESTIMATE OF LEAST SQUARES METHOD WITH LEAST DEVIATIONS FROM "ATTRACTION" POINTS FOR BILINEAR DYNAMIC SYSTEMS

  • Alexander S. Slabospitsky Faculty of Computer Science and Cybernetics, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Keywords: non-stationary parameter estimation, least squares method, ‘attraction’ points, variable forgetting factor, pseudo-inverse operator, recurrent algorithm, bilinear discrete dynamic system, weighted residual sum of squares

Abstract

The estimation problem of non-stationary parameter matrices is considered for bilinear discrete dynamic system in the case when for these unknown parameter matrices their ‘attraction’ points are known at any moment. Explicit and recurrent forms of representation are obtained for these parameter estimates of the least squares method with variable forgetting factor and least deviation norm from ‘attraction’ points under non-classical assumptions. The recurrent algorithm is also proposed for corresponding weighted residual sum of squares.

References

Eykhoff P. System Identification: Parameter and State Estimation. Chichester, England : Wiley, 1974. 555 p.

Ljung L. System Identification: Theory for the User. 2nd ed. Upper Saddle River, NJ : Prentice-Hall, 1999. 609 p.

Hsia T. C. System Identification. Least-squares Methods. Toronto : Lexington Books, 1977. 165 p.

Moore E. H. On the reciprocal of the general algebraic matrix. Bull. American Mathematical Society. 1920. Vol. 26, N 9. P. 394-395.

Penrose R. A generalized inverse for matrices. Proc. Cambridge Philoc. Soc. 1955. Vol. 51, N 3. P. 406-413.

Albert A. Regression and the Moore-Penrose Pseudoinverse. New York : Academic Press, 1972. 180 p.

Slabospitsky A.S. Recurrent least squares estimation algorithm with variable forgetting factor for non-classical assumptions. Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics. 1999. N 4. P. 237-240. (In Ukrainian)

Slabospitsky A.S. Recurrent estimation of nonstationary parameters by the least squares method with variable forgetting factor under non-classical assumptions. Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics. 2000. N 1. P. 282-285. (In Ukrainian)

Slabospitsky A.S. Use of additional information in the recurrent estimation of the parameters of discrete-time systems by the least squares method with non-classical assumptions. Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics. 2008. N 4. P. 179-182. (In Ukrainian)

Slabospitsky A.S. Estimation of nonstationary parameters by the least squares method with variable forgetting factor and minimum deviation from “gravity” points for systems under nonclassical assumptions. Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics. 2012. N 4. P. 199-202.

Slabospitsky A.S. Recurrent estimation of nonstationary system parameters under nonclassical least squares assumptions with variable forgetting factor and least deviation from “gravity” points. Journal of Computational and Applied Mathematics 2012. N 2 (108). P. 59-65. (In Ukrainian)

Slabospitsky A.S. A recurrent algorithm for estimating nonstationary parameters by the least squares method with the variable forgetting factor and the smallest deviations from the points of gravity for linear dynamic systems under nonclassical assumptions. Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics. 2016. N 3. P. 106-110. (In Ukrainian)

Slabospitsky A.S. Recurrent estimation of nonstationary parameters by the least squares method with variable forgetting factor and the smallest norm of deviation from the points of gravity for linear dynamic systems under nonclassical assumptions. Journal of Computational and Applied Mathematics. 2016. N 3 (123). P. 95-102. (In Ukrainian)

Published
2019-09-30