With the modern time series analysis method in the time domain and based on the autoregressive moving average (ARMA) innovation model and white noise estimators, new asymptotically stable multichannel optimal deconvolution filters in the ARMA innovation filter form and in the Wiener filter form are presented respectively.

For the target tracking systems with colored measurement noises,under the linear minimum variance information fusion criterion,three kinds of the multi-sensor information fusion steady-state Kalman filters weighted by matrices,diagonal matrices and scalars are obtained by two methods based on the ARMA innovation model and Riccati equation,respectively.

For the target tracking systems with the colored measurement noise, under the linear minimum variance information fusion criterion, three kinds of the multi-sensor information fusion steady-state Kalman filters weighted by matrices, diagonal matrices and scalars are obtained by two methods based on the ARMA innovation model and based on Riccati equation, respectively.

The innovation filtering interacting multiple model estimator(IFIMM) performs more accurate result than conventional IMM,but it may be imposed to slow down the model switching.

In order to solve the problem that innovation filtering interacting multiple model may slow down the model switching,an adaptive model transitionlFIMM algorithm is proposed.

In this paper, a method of process quality diagnosis using hypothesis testing for residual sequence of ARMA innovation model estimation error by recursive maximum likelihood method was studied.

A new adaptive Kalman filter based on ARMA innovation model is designed to detect weak high-frequency CW signal in strong Non-stationary noise environments.