Self-tuning of a Kalman Filter Applied in a DC Drive and in a Kalman-based Sensor

Kalman filters (KFs) are used in many different areas of application that require a solution to discrete-data linear filtering problems. Especially in the field of electric controls KFs represent a very used approach and an integral part of many states of the art of electric controls. However, the practical implementation of the KF often presents difficulties due to the challenging task of getting a good estimate of the covariance of the process noise represented by matrix Q
_k
and of the covariance of the measurement noise represented by matrix R
_k
. A fitting and simultaneous choice of the matrices Q
_k
and R
_k
based on a feedback loop within the KF realised by the filter samples can lead to a stable-operating filter after a reasonable amount of iterations. In this paper an approach to apply a feedback loop enabling dynamic values Q
_k
and R
_k
is presented. This approach will be applied in a simulation using Matlab/Simulink.