Kalman Filtering and Forecasting Algorithms with Use of Nonparametric Functional Estimators
The paper deals with the Kalman filtering and forecasting algorithms for a class of time-varying systems with unknown additive inputs. Such classes include object models with possible failures and also with models of controlled processes with unknown disturbances. The designed algorithms are based on combining the Kalman filter and nonparametric estimator. Examples are given to illustrate the usefulness of the proposed approach.
KeywordsKalman filtering and forecasting Unknown disturbances Nonparametric estimator
Work supported by Russian Foundation for Basic Research (projects 13-08-00744, 13-08-01015), Program for Improving the Competitiveness of TSU (Tomsk State University) among the Worlds Leading Scientific, and Laboratory of Geological Informatics of Computer Science Department of TSU.
- 3.Anderson, B.D.O., Moore, J.B.: Optimal Filtering. Prentice-Hall (1979)Google Scholar
- 10.Witczak, M.: Fault diagnosis and fault-tolerant control strategies for non-linear systems. Chapter 2. Unknown input observers and filters. Lecture Notes in Electrical Engineering, pp. 19–56, Springer International Publishing. Switzerland (2014)Google Scholar
- 13.Koshkin, G.M., Smagin, V.I.: Filtering and prediction for discrete systems with unknown input using nonparametric algorithms. In: Proceedings of 10th International Conference on Digital Technologies, pp. 120–124. Zilina, Slovakia, 9–11 July 2014Google Scholar
- 14.Dobrovidov, A., Koshkin, G., Vasiliev, V.: Non-parametric state space models. Heber, UT 84032, USA. Kendrick Press Inc. (2012)Google Scholar