Kalman filtering method based on recursion covariance matrix estimation

Abstract

The invention discloses a Kalman filtering method based on recursion covariance matrix estimation, and belongs to the field of self-adaptive filtering. The method mainly aims at a discrete time linear time invariant system model. In the method, in case that a system noise covariance matrix is completely unknown, a new statistical sequence can be constructed from an observation sequence of a system, by use of a recursion calculating covariance matrix estimation method designed on the basis of the law of large numbers, the covariance matrix estimation sequence of the newly constructed sequence can be calculated in real time, through the correlation between the covariance matrix constructing the sequence and the covariance matrix of process noise, an estimation sequence of a process noise covariance matrix can be calculated, and then the real-time estimation value of the covariance matrix of process noise is used to replace a covariance matrix of real process noise so as to be subjected to a Kalman filtering method for calculating a covariance matrix of real-time estimation and estimation deviations of system states through recursion. The method provided by the invention is suitable for standard Kalman filtering.

Description

technical field [0001] The invention belongs to the field of adaptive filtering, and in particular relates to an improved Kalman filtering method based on recursive covariance estimation. Background technique [0002] Since the Kalman filter theory was proposed in 1960, after more than 50 years of development, the Kalman filter theory has been theoretically promoted and applied in different engineering fields. [0003] Kalman filtering is a time-domain filtering method, which uses the state-space method to describe the system, that is, from the quantity measurement related to the extracted signal, the desired signal is estimated by the method. The estimated signal is a random response caused by white noise excitation, the transfer structure between the excitation source and the response is a system equation, and the functional relationship between the quantity measurement and the estimated quantity is a measurement equation. When the system equation and the measurement equa...

AI Technical Summary

Problems solved by technology

[0008] In view of this, the present invention provides a kind of improved Kalman filtering method based on recursive covariance matrix estimation method, the purpose is to solve the system state under the situation that the system noise covariance matrix in the discrete-time linear time-invariant system is completely unknown filter estimation problem

Images