This paper is concerned with an approach for identifying the input and observation noise covariances in continuous linear systems. The estimates of noise covariances are evaluated as the mean squares of Brownian motion processes conditioned upon all the available observation data. The suboptimal solutions are obtained in the sense that the differential equations for the evolution of the estimates are derived. Numerical examples for a simple system indicate acceptable performance of the proposed method.

This content is only available via PDF.
You do not currently have access to this content.