Fuzzy adaptive variational Bayesian unscented Kalman filter method

Abstract

The invention provides a fuzzy adaptive variational Bayesian unscented Kalman filter method. The method comprises the steps of estimating a one-step prediction target state as shown in the description and a covariance matrix thereof as shown in the description, iteratively estimating the variance as shown in the description of the measured noise, calculating the true value as shown in the description, the estimate value as shown in the description, the matching degree index as shown in the description and the adjustment quantity as shown in the description of a residual variance matrix at the current moment, and the adjusted measured noise variance as shown in the description, and calculating the estimated value as shown in the description of the target state and the error covariance matrix thereof. The method is capable of estimating the statistic variance capacity of the measured noise on line, and therefore, the filter error caused by unknown time variant of the noise statistical property is reduced and nonlinear filter estimation accuracy is improved. Meanwhile, the fuzzy logic method based on the innovated covariance matching technique is used for adjusting the measured noise variance estimated by the variational Bayesian method in real time, inhibiting the divergence of the filter and enhancing the robustness of the filter method.

Description

technical field [0001] The invention relates to a method in the technical field of signal processing, in particular to a fuzzy adaptive variational Bayesian unscented Kalman filtering method. Background technique [0002] Nonlinear stochastic dynamic systems are widely encountered in practical applications, such as rocket guidance and control systems, aircraft and ship inertial navigation systems, satellite orbit / attitude estimation, integrated navigation, radar or sonar detection And so on belong to this type of system. Even for linear systems, nonlinear filtering problems arise when states and parameters need to be estimated simultaneously. Moreover, nonlinear filtering problems widely exist in many scientific fields, so the state estimation of nonlinear systems is very important both in theory and in engineering. [0003] The most commonly used nonlinear system filtering method is extended Kalman filter (extended Kalman filter, EKF). EKF linearizes the nonlinear model ...

AI Technical Summary

Problems solved by technology

For practical application systems, the variance of measurement noise is always time-varying and unknown, because the measurement system is disturbed by various internal and external factors, including measurement errors and environmental disturbances, and the uncertainty of the statistical characteristics of this noise is often cause the existing filtering methods to fail

Images