Abstract:By the modem time series analysis method, based on the autoregressive moving average (ARMA) innovation model and white noise estimation theory, using the optimal fusion rule weighted by scalars for components, a component decoupled fusion Wiener state estimator is presented for the linear discrete stochastic descriptor systems with multisensor. The fused filtering, smoothing, and prediction problems can be handled in a unified framework and can handle non-cause decriptor system. In order to compute the optimal weights, the formula of computing the cross-covariances among local estimation errors is presented. Its accuracy is higher than that of each local estimator. A Monte Carlo simulation example shows its effectiveness.