Identification of Continuous Linear Time Invariant Systems Considering Stochastic Properties of Observation Noise

Abstract

In this paper, we discuss the identification of continuous linear time invariant systems with non-Gaussian observation noise. First we analyze the stochastic property of actual observation noise in terms of mixture distribution. Then we consider the method of data processing that converts the stochastic distribution of the noise in the actual observation to Gaussian distribution and propose a new identification method based on this data processing. Finally, we demonstrate the proposed identification method in both simulation and experiment.