An online detection method of fast Kalman filter based on dynamic parameter adjustment

Abstract

The invention discloses an online detection method based on dynamic parameter adjustment of fast Kalman filtering, comprising the following steps: placing an object to be detected in the same detection environment for pre-sampling to obtain several groups of noisy data, and calculating based on the noisy data The target value of the filtered data, the measurement variance of the filtered data, and the lower threshold of the Kalman gain; calculate the initial estimated value of the filtered data and the initial estimated variance value of the filtered data during the online detection process of the detection object; the initial estimated variance is based on the initial estimated value and the target value. The interval to which the error belongs to is determined; based on the initial estimated value and the initial estimated variance value, the Kalman filter correction recursive operation is performed until the filtering data converges to obtain the filtering data for the online detection of the detection object. The invention overcomes the problems of high iteration times and slow convergence speed caused by the unadjustable initial estimated value of the traditional Kalman filtering method through this method, and improves the timeliness of filtering detection.

Description

technical field [0001] The invention belongs to the technical field of signal filtering and processing, and in particular relates to an online detection method for fast Kalman filtering based on dynamic adjustment of parameters. Background technique [0002] Kalman filter is a method of optimally estimating the state of the system by observing the input and output data of the system by using the linear system state equation. At present, Kalman filter theory is widely used in communication systems, industrial control, radar signal processing, etc., among which it is widely used in time series analysis in the field of automatic detection. Nowadays, the computer programming implementation of Kalman filter theory is quite mature, but the traditional implementation method emphasizes the operation logic of modified recursion in Kalman filter theory, ignoring the direct influence of parameter settings on the results. [0003] At present, some adaptive Kalman filtering methods (AKF...

AI Technical Summary

Problems solved by technology

Nowadays, the computer programming implementation of Kalman filter theory is quite mature, but the traditional implementation method emphasizes the operation logic of corrective recursion in Kalman filter theory, ignoring the direct impact of parameter settings on the results

[0003] At present, some adaptive Kalman filter methods (AKF) have also made related improvements to parameter settings. Although they can suppress the defect of convergence time uncertainty caused by measurement random errors to a certain extent, there is still room for optimization in terms of timeliness. Difficult to meet the timeliness requirements of online testing

Images