Self-tuning Information Fusion Kalman Filter for Multichannel ARMA Signals

Abstract

For the multichannel autoregressive moving average (ARMA) signals with unknown model parameters and noise variances, the online information fusion estimators of model parameters and noise variances can be obtained, based on the system identification and correlation method. Then, by substituting them into the optimal fusion signal Kalman filter , a self-tuning fusion Kalman filter for the multichannel multisensor ARMA signal is presented. By applying the dynamic error system analysis (DESA) method, it is proven that the proposed self-tuning fusion signal Kalman filter converges to the optimal fusion signal Kalman filter in a realization, so that it obtains asymptotic optimality. A simulation example shows its effectiveness.