A Self-Tuning Filter for Nonstationary Arma Signals and its Applications
非平稳ARMA信号自校正滤波器及其应用

This paper deals with the estimation problem of nonstationary ARMA signals with white observation noise. Using the state-space method and the modern time series analysis method 1], based on ARMA innovation model. a self-tuning filter for nonstationary ARMA signals is presented. Hagander and Wittenmark's result for stationary ARMA signals is extended. Two simulation examples with application to the radar tracking system and the measurement data filtering are given, which show the applicability and usefulness of the proposed results.