Convergence of Optimal Linear Estimator With Multiplicative and Time-Correlated Additive Measurement Noises

In this paper, the problem of convergence for the optimal linear estimator of discrete-time linear systems with multiplicative and time-correlated additive measurement noises is studied. By defining a new random vector that consists of the innovation, error, and part of the noise in the new measurement obtained from the measurement differencing method, we obtain convergence conditions of the optimal linear estimator by equivalently studying the convergence of the expectation of a random matrix where the random matrix is the product of the new vector and its transpose. It is also shown that the state error covariance matrix of the optimal linear estimator converges to a unique fixed point under appropriate conditions and, moreover, this fixed point can be obtained by solving a set of matrix equations.

[1]  M. Srinath,et al.  Optimum Linear Estimation of Stochastic Signals in the Presence of Multiplicative Noise , 1971, IEEE Transactions on Aerospace and Electronic Systems.

[2]  Jitendra Tugnait.  Stability of optimum linear estimators of stochastic signals in white multiplicative noise , 1981 .

[3]  G. Lachapelle,et al.  Consideration of time-correlated errors in a Kalman filter applicable to GNSS , 2009 .

[4]  W. Liu.  Optimal filtering for discrete-time linear systems with multiplicative and time-correlated additive measurement noises , 2015 .

[5]  A. Stoica,et al.  A mixed H2 / H∞ estimation problem for linear systems with state dependent noise , 2011, IECON 2011 - 37th Annual Conference of the IEEE Industrial Electronics Society.

[6]  F. Lewis.  Optimal Estimation: With an Introduction to Stochastic Control Theory , 1986 .

[7]  Ju H. Park,et al.  Linear Optimal Estimation for Discrete-Time Measurement Delay Systems With Multichannel Multiplicative Noise , 2017, IEEE Transactions on Circuits and Systems II: Express Briefs.

[8]  A. E. Bryson,et al.  Estimation using sampled data containing sequentially correlated noise. , 1967 .

[9]  Ju H. Park,et al.  Linear Estimation for Measurement-Delay Systems With Periodic Coefficients and Multiplicative Noise , 2017, IEEE Transactions on Automatic Control.

[10]  Jeng-Shyang Pan,et al.  State estimation for discrete-time Markov jump linear systems with time-correlated and mode-dependent measurement noise , 2017, Autom..

[11]  F. Carravetta,et al.  Polynomial filtering of discrete-time stochastic linear systems with multiplicative state noise , 1997, IEEE Trans. Autom. Control..

[12]  Wei Liu,et al.  Optimal Estimation for Discrete-Time Linear Systems in the Presence of Multiplicative and Time-Correlated Additive Measurement Noises , 2015, IEEE Transactions on Signal Processing.

[13]  B. Chow,et al.  A new structure of recursive estimator , 1989 .

[14]  W. P. Birkemeier,et al.  A new recursive filter for systems with multiplicative noise , 1990, IEEE Trans. Inf. Theory.

[15]  Wei Liu,et al.  Optimal Filtering for Discrete-Time Linear Systems With Time-Correlated Multiplicative Measurement Noises , 2016, IEEE Transactions on Automatic Control.

[16]  Isaac Yaesh,et al.  Hinfinity control and filtering of discrete-time stochastic systems with multiplicative noise , 2001, Autom..

[17]  Willem L. De Koning,et al.  Optimal estimation of linear discrete-time systems with stochastic parameters , 1984, at - Automatisierungstechnik.

[18]  Wei Liu,et al.  State estimation for discrete-time Markov jump linear systems with time-correlated measurement noise , 2017, Autom..