Continuous--time model identification from noisy input/output measurements using fourth--order cumulants

Stéphane Thil (1) , Hugues Garnier (1) , Marion Gilson (1) , Kaushik Mahata (2)

1 CRAN - Centre de Recherche en Automatique de Nancy
2 School of Electrical Engineering and Computer Science

In this paper, the problem of identifying stochastic linear continuous-time systems from noisy input/output data is addressed. The input of the system is assumed to be non-Gaussian, whereas the noises contaminating the data are assumed to be Gaussian. The fourth-order cumulants of the input/output data are then (asymptotically) insensitive to the noises, that can be coloured and/or mutually correlated. Two estimators based on this noise-cancellation property are proposed. The performance of the proposed algorithms are assessed through a numerical simulation.

Mots clés: system identification; errors-in-variables; continuous-time systems; higher-order statistics

Domaines: Automatique / Robotique

Stéphane Thil, Hugues Garnier, Marion Gilson, Kaushik Mahata. Continuous--time model identification from noisy input/output measurements using fourth--order cumulants. 46th IEEE Conference on Decision and Control, CDC'07, Dec 2007, New Orleans, United States. pp.CDROM. ⟨hal-00167446⟩